Add ZH Normalization and i18n (#275)

* Add Chinese Normalization Part

* Fix function name

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Fix a bug

* Update webui.py

fix "some" bugs

* Update webui.py

fix function import folder

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Add i18n and move the package

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* delete old import part

* fix bugs...

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

fish_speech/i18n/locale/en_US.json

@@ -1,119 +1,122 @@
 {
-    "16-mixed is recommended for 10+ series GPU": "16-mixed is recommended for 10+ series GPU",
-    "5 to 10 seconds of reference audio, useful for specifying speaker.": "5 to 10 seconds of reference audio, useful for specifying speaker.",
-    "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).": "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).",
-    "Accumulate Gradient Batches": "Accumulate Gradient Batches",
-    "Add to Processing Area": "Add to Processing Area",
-    "Added path successfully!": "Added path successfully!",
-    "Advanced Config": "Advanced Config",
-    "Base LLAMA Model": "Base LLAMA Model",
-    "Batch Inference": "Batch Inference",
-    "Batch Size": "Batch Size",
-    "Changing with the Model Path": "Changing with the Model Path",
-    "Chinese": "Chinese",
-    "Compile Model": "Compile Model",
-    "Compile the model can significantly reduce the inference time, but will increase cold start time": "Compile the model can significantly reduce the inference time, but will increase cold start time",
-    "Copy": "Copy",
-    "Data Preprocessing": "Data Preprocessing",
-    "Data Preprocessing Path": "Data Preprocessing Path",
-    "Data Source": "Data Source",
-    "Decoder Model Config": "Decoder Model Config",
-    "Decoder Model Path": "Decoder Model Path",
-    "Disabled": "Disabled",
-    "Enable Reference Audio": "Enable Reference Audio",
-    "English": "English",
-    "Error Message": "Error Message",
-    "File Preprocessing": "File Preprocessing",
-    "Generate": "Generate",
-    "Generated Audio": "Generated Audio",
-    "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format": "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format",
-    "Infer interface is closed": "Infer interface is closed",
-    "Inference Configuration": "Inference Configuration",
-    "Inference Server Configuration": "Inference Server Configuration",
-    "Inference Server Error": "Inference Server Error",
-    "Inferring interface is launched at {}": "Inferring interface is launched at {}",
-    "Initial Learning Rate": "Initial Learning Rate",
-    "Input Audio & Source Path for Transcription": "Input Audio & Source Path for Transcription",
-    "Input Text": "Input Text",
-    "Invalid path: {}": "Invalid path: {}",
-    "It is recommended to use CUDA, if you have low configuration, use CPU": "It is recommended to use CUDA, if you have low configuration, use CPU",
-    "Iterative Prompt Length, 0 means off": "Iterative Prompt Length, 0 means off",
-    "Japanese": "Japanese",
-    "LLAMA Configuration": "LLAMA Configuration",
-    "LLAMA Model Config": "LLAMA Model Config",
-    "LLAMA Model Path": "LLAMA Model Path",
-    "Labeling Device": "Labeling Device",
-    "LoRA Model to be merged": "LoRA Model to be merged",
-    "Maximum Audio Duration": "Maximum Audio Duration",
-    "Maximum Length per Sample": "Maximum Length per Sample",
-    "Maximum Training Steps": "Maximum Training Steps",
-    "Maximum tokens per batch, 0 means no limit": "Maximum tokens per batch, 0 means no limit",
-    "Merge": "Merge",
-    "Merge LoRA": "Merge LoRA",
-    "Merge successfully": "Merge successfully",
-    "Minimum Audio Duration": "Minimum Audio Duration",
-    "Model Output Path": "Model Output Path",
-    "Model Size": "Model Size",
-    "Move": "Move",
-    "Move files successfully": "Move files successfully",
-    "No audio generated, please check the input text.": "No audio generated, please check the input text.",
-    "No selected options": "No selected options",
-    "Number of Workers": "Number of Workers",
-    "Open Inference Server": "Open Inference Server",
-    "Open Labeler WebUI": "Open Labeler WebUI",
-    "Open Tensorboard": "Open Tensorboard",
-    "Opened labeler in browser": "Opened labeler in browser",
-    "Optional Label Language": "Optional Label Language",
-    "Optional online ver": "Optional online ver",
-    "Output Path": "Output Path",
-    "Path error, please check the model file exists in the corresponding path": "Path error, please check the model file exists in the corresponding path",
-    "Precision": "Precision",
-    "Probability of applying Speaker Condition": "Probability of applying Speaker Condition",
-    "Put your text here.": "Put your text here.",
-    "Reference Audio": "Reference Audio",
-    "Reference Text": "Reference Text",
-    "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.",
-    "Remove Selected Data": "Remove Selected Data",
-    "Removed path successfully!": "Removed path successfully!",
-    "Repetition Penalty": "Repetition Penalty",
-    "Save model every n steps": "Save model every n steps",
-    "Select LLAMA ckpt": "Select LLAMA ckpt",
-    "Select VITS ckpt": "Select VITS ckpt",
-    "Select VQGAN ckpt": "Select VQGAN ckpt",
-    "Select source file processing method": "Select source file processing method",
-    "Select the model to be trained (Depending on the Tab page you are on)": "Select the model to be trained (Depending on the Tab page you are on)",
-    "Selected: {}": "Selected: {}",
-    "Speaker": "Speaker",
-    "Speaker is identified by the folder name": "Speaker is identified by the folder name",
-    "Start Training": "Start Training",
-    "Streaming Audio": "Streaming Audio",
-    "Streaming Generate": "Streaming Generate",
-    "Tensorboard Host": "Tensorboard Host",
-    "Tensorboard Log Path": "Tensorboard Log Path",
-    "Tensorboard Port": "Tensorboard Port",
-    "Tensorboard interface is closed": "Tensorboard interface is closed",
-    "Tensorboard interface is launched at {}": "Tensorboard interface is launched at {}",
-    "Text is too long, please keep it under {} characters.": "Text is too long, please keep it under {} characters.",
-    "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.": "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.",
-    "Training Configuration": "Training Configuration",
-    "Training Error": "Training Error",
-    "Training stopped": "Training stopped",
-    "Type name of the speaker": "Type name of the speaker",
-    "Type the path or select from the dropdown": "Type the path or select from the dropdown",
-    "Use LoRA": "Use LoRA",
-    "Use LoRA can save GPU memory, but may reduce the quality of the model": "Use LoRA can save GPU memory, but may reduce the quality of the model",
-    "Use filelist": "Use filelist",
-    "Use large for 10G+ GPU, medium for 5G, small for 2G": "Use large for 10G+ GPU, medium for 5G, small for 2G",
-    "VITS Configuration": "VITS Configuration",
-    "VQGAN Configuration": "VQGAN Configuration",
-    "Validation Batch Size": "Validation Batch Size",
-    "View the status of the preprocessing folder (use the slider to control the depth of the tree)": "View the status of the preprocessing folder (use the slider to control the depth of the tree)",
-    "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.": "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.",
-    "WebUI Host": "WebUI Host",
-    "WebUI Port": "WebUI Port",
-    "Whisper Model": "Whisper Model",
-    "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).": "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).",
-    "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU": "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU",
-    "latest": "latest",
-    "new": "new"
+  "16-mixed is recommended for 10+ series GPU": "16-mixed is recommended for 10+ series GPU",
+  "5 to 10 seconds of reference audio, useful for specifying speaker.": "5 to 10 seconds of reference audio, useful for specifying speaker.",
+  "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).": "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).",
+  "Accumulate Gradient Batches": "Accumulate Gradient Batches",
+  "Add to Processing Area": "Add to Processing Area",
+  "Added path successfully!": "Added path successfully!",
+  "Advanced Config": "Advanced Config",
+  "Base LLAMA Model": "Base LLAMA Model",
+  "Batch Inference": "Batch Inference",
+  "Batch Size": "Batch Size",
+  "Changing with the Model Path": "Changing with the Model Path",
+  "Chinese": "Chinese",
+  "Compile Model": "Compile Model",
+  "Compile the model can significantly reduce the inference time, but will increase cold start time": "Compile the model can significantly reduce the inference time, but will increase cold start time",
+  "Copy": "Copy",
+  "Data Preprocessing": "Data Preprocessing",
+  "Data Preprocessing Path": "Data Preprocessing Path",
+  "Data Source": "Data Source",
+  "Decoder Model Config": "Decoder Model Config",
+  "Decoder Model Path": "Decoder Model Path",
+  "Disabled": "Disabled",
+  "Enable Reference Audio": "Enable Reference Audio",
+  "English": "English",
+  "Error Message": "Error Message",
+  "File Preprocessing": "File Preprocessing",
+  "Generate": "Generate",
+  "Generated Audio": "Generated Audio",
+  "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format": "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format",
+  "Infer interface is closed": "Infer interface is closed",
+  "Inference Configuration": "Inference Configuration",
+  "Inference Server Configuration": "Inference Server Configuration",
+  "Inference Server Error": "Inference Server Error",
+  "Inferring interface is launched at {}": "Inferring interface is launched at {}",
+  "Initial Learning Rate": "Initial Learning Rate",
+  "Input Audio & Source Path for Transcription": "Input Audio & Source Path for Transcription",
+  "Input Text": "Input Text",
+  "Invalid path: {}": "Invalid path: {}",
+  "It is recommended to use CUDA, if you have low configuration, use CPU": "It is recommended to use CUDA, if you have low configuration, use CPU",
+  "Iterative Prompt Length, 0 means off": "Iterative Prompt Length, 0 means off",
+  "Japanese": "Japanese",
+  "LLAMA Configuration": "LLAMA Configuration",
+  "LLAMA Model Config": "LLAMA Model Config",
+  "LLAMA Model Path": "LLAMA Model Path",
+  "Labeling Device": "Labeling Device",
+  "LoRA Model to be merged": "LoRA Model to be merged",
+  "Maximum Audio Duration": "Maximum Audio Duration",
+  "Maximum Length per Sample": "Maximum Length per Sample",
+  "Maximum Training Steps": "Maximum Training Steps",
+  "Maximum tokens per batch, 0 means no limit": "Maximum tokens per batch, 0 means no limit",
+  "Merge": "Merge",
+  "Merge LoRA": "Merge LoRA",
+  "Merge successfully": "Merge successfully",
+  "Minimum Audio Duration": "Minimum Audio Duration",
+  "Model Output Path": "Model Output Path",
+  "Model Size": "Model Size",
+  "Move": "Move",
+  "Move files successfully": "Move files successfully",
+  "No audio generated, please check the input text.": "No audio generated, please check the input text.",
+  "No selected options": "No selected options",
+  "Number of Workers": "Number of Workers",
+  "Open Inference Server": "Open Inference Server",
+  "Open Labeler WebUI": "Open Labeler WebUI",
+  "Open Tensorboard": "Open Tensorboard",
+  "Opened labeler in browser": "Opened labeler in browser",
+  "Optional Label Language": "Optional Label Language",
+  "Optional online ver": "Optional online ver",
+  "Output Path": "Output Path",
+  "Path error, please check the model file exists in the corresponding path": "Path error, please check the model file exists in the corresponding path",
+  "Precision": "Precision",
+  "Probability of applying Speaker Condition": "Probability of applying Speaker Condition",
+  "Put your text here.": "Put your text here.",
+  "Reference Audio": "Reference Audio",
+  "Reference Text": "Reference Text",
+  "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.",
+  "Remove Selected Data": "Remove Selected Data",
+  "Removed path successfully!": "Removed path successfully!",
+  "Repetition Penalty": "Repetition Penalty",
+  "Save model every n steps": "Save model every n steps",
+  "Select LLAMA ckpt": "Select LLAMA ckpt",
+  "Select VITS ckpt": "Select VITS ckpt",
+  "Select VQGAN ckpt": "Select VQGAN ckpt",
+  "Select source file processing method": "Select source file processing method",
+  "Select the model to be trained (Depending on the Tab page you are on)": "Select the model to be trained (Depending on the Tab page you are on)",
+  "Selected: {}": "Selected: {}",
+  "Speaker": "Speaker",
+  "Speaker is identified by the folder name": "Speaker is identified by the folder name",
+  "Start Training": "Start Training",
+  "Streaming Audio": "Streaming Audio",
+  "Streaming Generate": "Streaming Generate",
+  "Tensorboard Host": "Tensorboard Host",
+  "Tensorboard Log Path": "Tensorboard Log Path",
+  "Tensorboard Port": "Tensorboard Port",
+  "Tensorboard interface is closed": "Tensorboard interface is closed",
+  "Tensorboard interface is launched at {}": "Tensorboard interface is launched at {}",
+  "Text is too long, please keep it under {} characters.": "Text is too long, please keep it under {} characters.",
+  "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.": "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.",
+  "Training Configuration": "Training Configuration",
+  "Training Error": "Training Error",
+  "Training stopped": "Training stopped",
+  "Type name of the speaker": "Type name of the speaker",
+  "Type the path or select from the dropdown": "Type the path or select from the dropdown",
+  "Use LoRA": "Use LoRA",
+  "Use LoRA can save GPU memory, but may reduce the quality of the model": "Use LoRA can save GPU memory, but may reduce the quality of the model",
+  "Use filelist": "Use filelist",
+  "Use large for 10G+ GPU, medium for 5G, small for 2G": "Use large for 10G+ GPU, medium for 5G, small for 2G",
+  "VITS Configuration": "VITS Configuration",
+  "VQGAN Configuration": "VQGAN Configuration",
+  "Validation Batch Size": "Validation Batch Size",
+  "View the status of the preprocessing folder (use the slider to control the depth of the tree)": "View the status of the preprocessing folder (use the slider to control the depth of the tree)",
+  "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.": "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.",
+  "WebUI Host": "WebUI Host",
+  "WebUI Port": "WebUI Port",
+  "Whisper Model": "Whisper Model",
+  "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).": "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).",
+  "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU": "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU",
+  "latest": "latest",
+  "new": "new",
+  "Realtime Transform Text": "Realtime Transform Text",
+  "Normalization Result Preview (Currently Only Chinese)": "Normalization Result Preview (Currently Only Chinese)",
+  "Text Normalization": "Text Normalization"
 }

fish_speech/i18n/locale/es_ES.json

@@ -1,119 +1,122 @@
 {
-    "16-mixed is recommended for 10+ series GPU": "se recomienda 16-mixed para GPU de la serie 10+",
-    "5 to 10 seconds of reference audio, useful for specifying speaker.": "5 a 10 segundos de audio de referencia, útil para especificar el hablante.",
-    "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).": "Un modelo de texto a voz basado en VQ-GAN y Llama desarrollado por [Fish Audio](https://fish.audio).",
-    "Accumulate Gradient Batches": "Acumular lotes de gradientes",
-    "Add to Processing Area": "Agregar al Área de Procesamiento",
-    "Added path successfully!": "¡Ruta agregada exitosamente!",
-    "Advanced Config": "Configuración Avanzada",
-    "Base LLAMA Model": "Modelo Base LLAMA",
-    "Batch Inference": "Inferencia por Lote",
-    "Batch Size": "Tamaño del Lote",
-    "Changing with the Model Path": "Cambiando con la Ruta del Modelo",
-    "Chinese": "Chino",
-    "Compile Model": "Compilar Modelo",
-    "Compile the model can significantly reduce the inference time, but will increase cold start time": "Compilar el modelo puede reducir significativamente el tiempo de inferencia, pero aumentará el tiempo de inicio en frío",
-    "Copy": "Copiar",
-    "Data Preprocessing": "Preprocesamiento de Datos",
-    "Data Preprocessing Path": "Ruta de Preprocesamiento de Datos",
-    "Data Source": "Fuente de Datos",
-    "Decoder Model Config": "Configuración del modelo decodificador",
-    "Decoder Model Path": "Ruta del modelo decodificador",
-    "Disabled": "Desactivado",
-    "Enable Reference Audio": "Habilitar Audio de Referencia",
-    "English": "Inglés",
-    "Error Message": "Mensaje de Error",
-    "File Preprocessing": "Preprocesamiento de Archivos",
-    "Generate": "Generar",
-    "Generated Audio": "Audio Generado",
-    "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format": "Si no hay texto correspondiente para el audio, aplique ASR para asistencia, soporte para formato .txt o .lab",
-    "Infer interface is closed": "La interfaz de inferencia está cerrada",
-    "Inference Configuration": "Configuración de Inferencia",
-    "Inference Server Configuration": "Configuración del Servidor de Inferencia",
-    "Inference Server Error": "Error del Servidor de Inferencia",
-    "Inferring interface is launched at {}": "La interfaz de inferencia se ha lanzado en {}",
-    "Initial Learning Rate": "Tasa de Aprendizaje Inicial",
-    "Input Audio & Source Path for Transcription": "Audio de Entrada y Ruta de Origen para Transcripción",
-    "Input Text": "Texto de Entrada",
-    "Invalid path: {}": "Ruta inválida: {}",
-    "It is recommended to use CUDA, if you have low configuration, use CPU": "Se recomienda usar CUDA, si tiene una configuración baja, use CPU",
-    "Iterative Prompt Length, 0 means off": "Longitud de la Indicación Iterativa, 0 significa apagado",
-    "Japanese": "Japonés",
-    "LLAMA Configuration": "Configuración de LLAMA",
-    "LLAMA Model Config": "Configuración del Modelo LLAMA",
-    "LLAMA Model Path": "Ruta del Modelo LLAMA",
-    "Labeling Device": "Dispositivo de Etiquetado",
-    "LoRA Model to be merged": "Modelo LoRA a fusionar",
-    "Maximum Audio Duration": "Duración máxima de audio",
-    "Maximum Length per Sample": "Longitud Máxima por Muestra",
-    "Maximum Training Steps": "Pasos Máximos de Entrenamiento",
-    "Maximum tokens per batch, 0 means no limit": "Máximo de tokens por lote, 0 significa sin límite",
-    "Merge": "Fusionar",
-    "Merge LoRA": "Fusionar LoRA",
-    "Merge successfully": "Fusionado exitosamente",
-    "Minimum Audio Duration": "Duración mínima de audio",
-    "Model Output Path": "Ruta de Salida del Modelo",
-    "Model Size": "Tamaño del Modelo",
-    "Move": "Mover",
-    "Move files successfully": "Archivos movidos exitosamente",
-    "No audio generated, please check the input text.": "No se generó audio, por favor verifique el texto de entrada.",
-    "No selected options": "No hay opciones seleccionadas",
-    "Number of Workers": "Número de Trabajadores",
-    "Open Inference Server": "Abrir Servidor de Inferencia",
-    "Open Labeler WebUI": "Abrir Interfaz Web del Etiquetador",
-    "Open Tensorboard": "Abrir Tensorboard",
-    "Opened labeler in browser": "Se abrió el etiquetador en el navegador",
-    "Optional Label Language": "Idioma de Etiquetado Opcional",
-    "Optional online ver": "Ver en línea opcional",
-    "Output Path": "Ruta de Salida",
-    "Path error, please check the model file exists in the corresponding path": "Error de ruta, por favor verifique que el archivo del modelo exista en la ruta correspondiente",
-    "Precision": "Precisión",
-    "Probability of applying Speaker Condition": "Probabilidad de aplicar Condición de Hablante",
-    "Put your text here.": "Ponga su texto aquí.",
-    "Reference Audio": "Audio de Referencia",
-    "Reference Text": "Texto de Referencia",
-    "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "El código relacionado se publica bajo la Licencia BSD-3-Clause, y los pesos se publican bajo la Licencia CC BY-NC-SA 4.0.",
-    "Remove Selected Data": "Eliminar Datos Seleccionados",
-    "Removed path successfully!": "¡Ruta eliminada exitosamente!",
-    "Repetition Penalty": "Penalización por Repetición",
-    "Save model every n steps": "Guardar modelo cada n pasos",
-    "Select LLAMA ckpt": "Seleccionar punto de control LLAMA",
-    "Select VITS ckpt": "Seleccionar punto de control VITS",
-    "Select VQGAN ckpt": "Seleccionar punto de control VQGAN",
-    "Select source file processing method": "Seleccione el método de procesamiento de archivos fuente",
-    "Select the model to be trained (Depending on the Tab page you are on)": "Seleccione el modelo a entrenar (Dependiendo de la pestaña en la que se encuentre)",
-    "Selected: {}": "Seleccionado: {}",
-    "Speaker": "Hablante",
-    "Speaker is identified by the folder name": "El hablante se identifica por el nombre de la carpeta",
-    "Start Training": "Iniciar Entrenamiento",
-    "Streaming Audio": "transmisión de audio",
-    "Streaming Generate": "síntesis en flujo",
-    "Tensorboard Host": "Host de Tensorboard",
-    "Tensorboard Log Path": "Ruta de Registro de Tensorboard",
-    "Tensorboard Port": "Puerto de Tensorboard",
-    "Tensorboard interface is closed": "La interfaz de Tensorboard está cerrada",
-    "Tensorboard interface is launched at {}": "La interfaz de Tensorboard se ha lanzado en {}",
-    "Text is too long, please keep it under {} characters.": "El texto es demasiado largo, por favor manténgalo por debajo de {} caracteres.",
-    "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.": "La ruta de la carpeta de entrada a la izquierda o la lista de archivos. Ya sea que esté marcado o no, se utilizará para el entrenamiento posterior en esta lista.",
-    "Training Configuration": "Configuración de Entrenamiento",
-    "Training Error": "Error de Entrenamiento",
-    "Training stopped": "Entrenamiento detenido",
-    "Type name of the speaker": "Escriba el nombre del hablante",
-    "Type the path or select from the dropdown": "Escriba la ruta o seleccione de la lista desplegable",
-    "Use LoRA": "Usar LoRA",
-    "Use LoRA can save GPU memory, but may reduce the quality of the model": "Usar LoRA puede ahorrar memoria GPU, pero puede reducir la calidad del modelo",
-    "Use filelist": "Usar lista de archivos",
-    "Use large for 10G+ GPU, medium for 5G, small for 2G": "Use grande para GPU de 10G+, mediano para 5G, pequeño para 2G",
-    "VITS Configuration": "Configuración de VITS",
-    "VQGAN Configuration": "Configuración de VQGAN",
-    "Validation Batch Size": "Tamaño del Lote de Validación",
-    "View the status of the preprocessing folder (use the slider to control the depth of the tree)": "Vea el estado de la carpeta de preprocesamiento (use el control deslizante para controlar la profundidad del árbol)",
-    "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.": "No somos responsables de ningún mal uso del modelo, por favor considere sus leyes y regulaciones locales antes de usarlo.",
-    "WebUI Host": "Host de WebUI",
-    "WebUI Port": "Puerto de WebUI",
-    "Whisper Model": "Modelo Whisper",
-    "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).": "Puede encontrar el código fuente [aquí](https://github.com/fishaudio/fish-speech) y los modelos [aquí](https://huggingface.co/fishaudio/fish-speech-1).",
-    "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU": "Se recomienda bf16-true para GPU de la serie 30+, se recomienda 16-mixed para GPU de la serie 10+",
-    "latest": "más reciente",
-    "new": "nuevo"
+  "16-mixed is recommended for 10+ series GPU": "se recomienda 16-mixed para GPU de la serie 10+",
+  "5 to 10 seconds of reference audio, useful for specifying speaker.": "5 a 10 segundos de audio de referencia, útil para especificar el hablante.",
+  "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).": "Un modelo de texto a voz basado en VQ-GAN y Llama desarrollado por [Fish Audio](https://fish.audio).",
+  "Accumulate Gradient Batches": "Acumular lotes de gradientes",
+  "Add to Processing Area": "Agregar al Área de Procesamiento",
+  "Added path successfully!": "¡Ruta agregada exitosamente!",
+  "Advanced Config": "Configuración Avanzada",
+  "Base LLAMA Model": "Modelo Base LLAMA",
+  "Batch Inference": "Inferencia por Lote",
+  "Batch Size": "Tamaño del Lote",
+  "Changing with the Model Path": "Cambiando con la Ruta del Modelo",
+  "Chinese": "Chino",
+  "Compile Model": "Compilar Modelo",
+  "Compile the model can significantly reduce the inference time, but will increase cold start time": "Compilar el modelo puede reducir significativamente el tiempo de inferencia, pero aumentará el tiempo de inicio en frío",
+  "Copy": "Copiar",
+  "Data Preprocessing": "Preprocesamiento de Datos",
+  "Data Preprocessing Path": "Ruta de Preprocesamiento de Datos",
+  "Data Source": "Fuente de Datos",
+  "Decoder Model Config": "Configuración del modelo decodificador",
+  "Decoder Model Path": "Ruta del modelo decodificador",
+  "Disabled": "Desactivado",
+  "Enable Reference Audio": "Habilitar Audio de Referencia",
+  "English": "Inglés",
+  "Error Message": "Mensaje de Error",
+  "File Preprocessing": "Preprocesamiento de Archivos",
+  "Generate": "Generar",
+  "Generated Audio": "Audio Generado",
+  "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format": "Si no hay texto correspondiente para el audio, aplique ASR para asistencia, soporte para formato .txt o .lab",
+  "Infer interface is closed": "La interfaz de inferencia está cerrada",
+  "Inference Configuration": "Configuración de Inferencia",
+  "Inference Server Configuration": "Configuración del Servidor de Inferencia",
+  "Inference Server Error": "Error del Servidor de Inferencia",
+  "Inferring interface is launched at {}": "La interfaz de inferencia se ha lanzado en {}",
+  "Initial Learning Rate": "Tasa de Aprendizaje Inicial",
+  "Input Audio & Source Path for Transcription": "Audio de Entrada y Ruta de Origen para Transcripción",
+  "Input Text": "Texto de Entrada",
+  "Invalid path: {}": "Ruta inválida: {}",
+  "It is recommended to use CUDA, if you have low configuration, use CPU": "Se recomienda usar CUDA, si tiene una configuración baja, use CPU",
+  "Iterative Prompt Length, 0 means off": "Longitud de la Indicación Iterativa, 0 significa apagado",
+  "Japanese": "Japonés",
+  "LLAMA Configuration": "Configuración de LLAMA",
+  "LLAMA Model Config": "Configuración del Modelo LLAMA",
+  "LLAMA Model Path": "Ruta del Modelo LLAMA",
+  "Labeling Device": "Dispositivo de Etiquetado",
+  "LoRA Model to be merged": "Modelo LoRA a fusionar",
+  "Maximum Audio Duration": "Duración máxima de audio",
+  "Maximum Length per Sample": "Longitud Máxima por Muestra",
+  "Maximum Training Steps": "Pasos Máximos de Entrenamiento",
+  "Maximum tokens per batch, 0 means no limit": "Máximo de tokens por lote, 0 significa sin límite",
+  "Merge": "Fusionar",
+  "Merge LoRA": "Fusionar LoRA",
+  "Merge successfully": "Fusionado exitosamente",
+  "Minimum Audio Duration": "Duración mínima de audio",
+  "Model Output Path": "Ruta de Salida del Modelo",
+  "Model Size": "Tamaño del Modelo",
+  "Move": "Mover",
+  "Move files successfully": "Archivos movidos exitosamente",
+  "No audio generated, please check the input text.": "No se generó audio, por favor verifique el texto de entrada.",
+  "No selected options": "No hay opciones seleccionadas",
+  "Number of Workers": "Número de Trabajadores",
+  "Open Inference Server": "Abrir Servidor de Inferencia",
+  "Open Labeler WebUI": "Abrir Interfaz Web del Etiquetador",
+  "Open Tensorboard": "Abrir Tensorboard",
+  "Opened labeler in browser": "Se abrió el etiquetador en el navegador",
+  "Optional Label Language": "Idioma de Etiquetado Opcional",
+  "Optional online ver": "Ver en línea opcional",
+  "Output Path": "Ruta de Salida",
+  "Path error, please check the model file exists in the corresponding path": "Error de ruta, por favor verifique que el archivo del modelo exista en la ruta correspondiente",
+  "Precision": "Precisión",
+  "Probability of applying Speaker Condition": "Probabilidad de aplicar Condición de Hablante",
+  "Put your text here.": "Ponga su texto aquí.",
+  "Reference Audio": "Audio de Referencia",
+  "Reference Text": "Texto de Referencia",
+  "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "El código relacionado se publica bajo la Licencia BSD-3-Clause, y los pesos se publican bajo la Licencia CC BY-NC-SA 4.0.",
+  "Remove Selected Data": "Eliminar Datos Seleccionados",
+  "Removed path successfully!": "¡Ruta eliminada exitosamente!",
+  "Repetition Penalty": "Penalización por Repetición",
+  "Save model every n steps": "Guardar modelo cada n pasos",
+  "Select LLAMA ckpt": "Seleccionar punto de control LLAMA",
+  "Select VITS ckpt": "Seleccionar punto de control VITS",
+  "Select VQGAN ckpt": "Seleccionar punto de control VQGAN",
+  "Select source file processing method": "Seleccione el método de procesamiento de archivos fuente",
+  "Select the model to be trained (Depending on the Tab page you are on)": "Seleccione el modelo a entrenar (Dependiendo de la pestaña en la que se encuentre)",
+  "Selected: {}": "Seleccionado: {}",
+  "Speaker": "Hablante",
+  "Speaker is identified by the folder name": "El hablante se identifica por el nombre de la carpeta",
+  "Start Training": "Iniciar Entrenamiento",
+  "Streaming Audio": "transmisión de audio",
+  "Streaming Generate": "síntesis en flujo",
+  "Tensorboard Host": "Host de Tensorboard",
+  "Tensorboard Log Path": "Ruta de Registro de Tensorboard",
+  "Tensorboard Port": "Puerto de Tensorboard",
+  "Tensorboard interface is closed": "La interfaz de Tensorboard está cerrada",
+  "Tensorboard interface is launched at {}": "La interfaz de Tensorboard se ha lanzado en {}",
+  "Text is too long, please keep it under {} characters.": "El texto es demasiado largo, por favor manténgalo por debajo de {} caracteres.",
+  "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.": "La ruta de la carpeta de entrada a la izquierda o la lista de archivos. Ya sea que esté marcado o no, se utilizará para el entrenamiento posterior en esta lista.",
+  "Training Configuration": "Configuración de Entrenamiento",
+  "Training Error": "Error de Entrenamiento",
+  "Training stopped": "Entrenamiento detenido",
+  "Type name of the speaker": "Escriba el nombre del hablante",
+  "Type the path or select from the dropdown": "Escriba la ruta o seleccione de la lista desplegable",
+  "Use LoRA": "Usar LoRA",
+  "Use LoRA can save GPU memory, but may reduce the quality of the model": "Usar LoRA puede ahorrar memoria GPU, pero puede reducir la calidad del modelo",
+  "Use filelist": "Usar lista de archivos",
+  "Use large for 10G+ GPU, medium for 5G, small for 2G": "Use grande para GPU de 10G+, mediano para 5G, pequeño para 2G",
+  "VITS Configuration": "Configuración de VITS",
+  "VQGAN Configuration": "Configuración de VQGAN",
+  "Validation Batch Size": "Tamaño del Lote de Validación",
+  "View the status of the preprocessing folder (use the slider to control the depth of the tree)": "Vea el estado de la carpeta de preprocesamiento (use el control deslizante para controlar la profundidad del árbol)",
+  "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.": "No somos responsables de ningún mal uso del modelo, por favor considere sus leyes y regulaciones locales antes de usarlo.",
+  "WebUI Host": "Host de WebUI",
+  "WebUI Port": "Puerto de WebUI",
+  "Whisper Model": "Modelo Whisper",
+  "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).": "Puede encontrar el código fuente [aquí](https://github.com/fishaudio/fish-speech) y los modelos [aquí](https://huggingface.co/fishaudio/fish-speech-1).",
+  "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU": "Se recomienda bf16-true para GPU de la serie 30+, se recomienda 16-mixed para GPU de la serie 10+",
+  "latest": "más reciente",
+  "new": "nuevo",
+  "Realtime Transform Text": "Transformación de Texto en Tiempo Real",
+  "Normalization Result Preview (Currently Only Chinese)": "Vista Previa del Resultado de Normalización (Actualmente Solo Chino)",
+  "Text Normalization": "Normalización de Texto"
 }

fish_speech/i18n/locale/ja_JP.json

@@ -1,119 +1,123 @@
 {
-    "16-mixed is recommended for 10+ series GPU": "10シリーズ以降のGPUには16-mixedをお勧めします",
-    "5 to 10 seconds of reference audio, useful for specifying speaker.": "話者を指定するのに役立つ、5～10秒のリファレンスオーディオ。",
-    "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).": "[Fish Audio](https://fish.audio)が開発したVQ-GANとLlamaに基づくテキスト音声合成モデル。",
-    "Accumulate Gradient Batches": "勾配バッチの累積",
-    "Add to Processing Area": "処理エリアに追加",
-    "Added path successfully!": "パスの追加に成功しました！",
-    "Advanced Config": "詳細設定",
-    "Base LLAMA Model": "基本LLAMAモデル",
-    "Batch Inference": "バッチ推論",
-    "Batch Size": "バッチサイズ",
-    "Changing with the Model Path": "モデルのパスに伴って変化する",
-    "Chinese": "中国語",
-    "Compile Model": "モデルのコンパイル",
-    "Compile the model can significantly reduce the inference time, but will increase cold start time": "モデルをコンパイルすると推論時間を大幅に短縮できますが、コールドスタート時間が長くなります",
-    "Copy": "コピー",
-    "Data Preprocessing": "データ前処理",
-    "Data Preprocessing Path": "データ前処理パス",
-    "Data Source": "データソース",
-    "Decoder Model Config": "デコーダーモデルの構成",
-    "Decoder Model Path": "デコーダーモデルのパス",
-    "Disabled": "無効",
-    "Enable Reference Audio": "リファレンスオーディオを有効にする",
-    "English": "英語",
-    "Error Message": "エラーメッセージ",
-    "File Preprocessing": "文書前处理",
-    "Generate": "生成",
-    "Generated Audio": "生成されたオーディオ",
-    "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format": "音声に対応するテキストがない場合は、ASRを適用してサポートします。.txtまたは.lab形式をサポートしています",
-    "Infer interface is closed": "推論インターフェースが閉じられています",
-    "Inference Configuration": "推論設定",
-    "Inference Server Configuration": "推論サーバー設定",
-    "Inference Server Error": "推論サーバーエラー",
-    "Inferring interface is launched at {}": "推論インターフェースが{}で起動しました",
-    "Initial Learning Rate": "初期学習率",
-    "Input Audio & Source Path for Transcription": "入力オーディオと文字起こしのソースパス",
-    "Input Text": "入力テキスト",
-    "Invalid path: {}": "無効なパス: {}",
-    "It is recommended to use CUDA, if you have low configuration, use CPU": "CUDAの使用をお勧めします。低い構成の場合はCPUを使用してください",
-    "Iterative Prompt Length, 0 means off": "反復プロンプト長。0はオフを意味します",
-    "Japanese": "日本語",
-    "LLAMA Configuration": "LLAMA設定",
-    "LLAMA Model Config": "LLAMAモデル設定",
-    "LLAMA Model Path": "LLAMAモデルパス",
-    "Labeling Device": "ラベリングデバイス",
-    "LoRA Model to be merged": "マージするLoRAモデル",
-    "Maximum Audio Duration": "最大オーディオの長さ",
-    "Maximum Length per Sample": "サンプルあたりの最大長",
-    "Maximum Training Steps": "最大トレーニングステップ数",
-    "Maximum tokens per batch, 0 means no limit": "バッチあたりの最大トークン数。0は制限なしを意味します",
-    "Merge": "マージ",
-    "Merge LoRA": "LoRAのマージ",
-    "Merge successfully": "マージに成功しました",
-    "Minimum Audio Duration": "最小オーディオの長さ",
-    "Model Output Path": "モデル出力パス",
-    "Model Size": "モデルサイズ",
-    "Move": "移動",
-    "Move files successfully": "ファイルの移動に成功しました",
-    "No audio generated, please check the input text.": "オーディオが生成されていません。入力テキストを確認してください。",
-    "No selected options": "選択されたオプションはありません",
-    "Number of Workers": "ワーカー数",
-    "Open Inference Server": "推論サーバーを開く",
-    "Open Labeler WebUI": "ラベラーWebUIを開く",
-    "Open Tensorboard": "Tensorboardを開く",
-    "Opened labeler in browser": "ブラウザでラベラーを開きました",
-    "Optional Label Language": "オプションのラベル言語",
-    "Optional online ver": "オプションのオンラインバージョン",
-    "Output Path": "出力パス",
-    "Path error, please check the model file exists in the corresponding path": "パスエラー。対応するパスにモデルファイルが存在するか確認してください",
-    "Precision": "精度",
-    "Probability of applying Speaker Condition": "話者条件を適用する確率",
-    "Put your text here.": "ここにテキストを入力してください。",
-    "Reference Audio": "リファレンスオーディオ",
-    "Reference Text": "リファレンステキスト",
-    "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "関連コードはBSD-3-Clauseライセンスの下でリリースされ、重みはCC BY-NC-SA 4.0ライセンスの下でリリースされます。",
-    "Remove Selected Data": "選択したデータを削除",
-    "Removed path successfully!": "パスの削除に成功しました！",
-    "Repetition Penalty": "反復ペナルティ",
-    "Save model every n steps": "nステップごとにモデルを保存",
-    "Select LLAMA ckpt": " LLAMA チェックポイントを選択",
-    "Select VITS ckpt": "VITS チェックポイントを選択",
-    "Select VQGAN ckpt": "VQGAN チェックポイントを選択",
-    "Select source file processing method": "ソースファイルの処理方法を選択",
-    "Select the model to be trained (Depending on the Tab page you are on)": "タブページに応じてトレーニングするモデルを選択してください",
-    "Selected: {}": "選択済み: {}",
-    "Speaker": "話者",
-    "Speaker is identified by the folder name": "話者はフォルダ名で識別されます",
-    "Start Training": "トレーニング開始",
-    "Streaming Audio": "ストリーミングオーディオ",
-    "Streaming Generate": "ストリーミング合成",
-    "Tensorboard Host": "Tensorboardホスト",
-    "Tensorboard Log Path": "Tensorboardログパス",
-    "Tensorboard Port": "Tensorboardポート",
-    "Tensorboard interface is closed": "Tensorboardインターフェースが閉じられています",
-    "Tensorboard interface is launched at {}": "Tensorboardインターフェースが{}で起動されました",
-    "Text is too long, please keep it under {} characters.": "テキストが長すぎます。{}文字以内に抑えてください。",
-    "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.": "左側の入力フォルダまたはファイルリストのパス。チェックの有無にかかわらず、このリストの後続のトレーニングに使用されます。",
-    "Training Configuration": "トレーニング設定",
-    "Training Error": "トレーニングエラー",
-    "Training stopped": "トレーニングが停止しました",
-    "Type name of the speaker": "話者の名前を入力",
-    "Type the path or select from the dropdown": "パスを入力するか、ドロップダウンから選択してください",
-    "Use LoRA": "LoRAを使用",
-    "Use LoRA can save GPU memory, but may reduce the quality of the model": "LoRAを使用するとGPUメモリを節約できますが、モデルの品質が低下する可能性があります",
-    "Use filelist": "ファイルリストを使用",
-    "Use large for 10G+ GPU, medium for 5G, small for 2G": "10G以上のGPUには大、5Gには中、2Gには小を使用してください",
-    "VITS Configuration": "VITS の構成",
-    "VQGAN Configuration": "VQGAN の構成",
-    "Validation Batch Size": "検証バッチサイズ",
-    "View the status of the preprocessing folder (use the slider to control the depth of the tree)": "前処理フォルダの状態を表示（スライダーを使用してツリーの深さを制御）",
-    "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.": "モデルの誤用については一切責任を負いません。使用する前に、現地の法律と規制を考慮してください。",
-    "WebUI Host": "WebUIホスト",
-    "WebUI Port": "WebUIポート",
-    "Whisper Model": "Whisperモデル",
-    "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).": "ソースコードは[こちら](https://github.com/fishaudio/fish-speech)、モデルは[こちら](https://huggingface.co/fishaudio/fish-speech-1)にあります。",
-    "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU": "30シリーズ以降のGPUにはbf16-trueを、10シリーズ以降のGPUには16-mixedをお勧めします",
-    "latest": "最新",
-    "new": "新規"
+  "16-mixed is recommended for 10+ series GPU": "10シリーズ以降のGPUには16-mixedをお勧めします",
+  "5 to 10 seconds of reference audio, useful for specifying speaker.": "話者を指定するのに役立つ、5～10秒のリファレンスオーディオ。",
+  "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).": "[Fish Audio](https://fish.audio)が開発したVQ-GANとLlamaに基づくテキスト音声合成モデル。",
+  "Accumulate Gradient Batches": "勾配バッチの累積",
+  "Add to Processing Area": "処理エリアに追加",
+  "Added path successfully!": "パスの追加に成功しました！",
+  "Advanced Config": "詳細設定",
+  "Base LLAMA Model": "基本LLAMAモデル",
+  "Batch Inference": "バッチ推論",
+  "Batch Size": "バッチサイズ",
+  "Changing with the Model Path": "モデルのパスに伴って変化する",
+  "Chinese": "中国語",
+  "Compile Model": "モデルのコンパイル",
+  "Compile the model can significantly reduce the inference time, but will increase cold start time": "モデルをコンパイルすると推論時間を大幅に短縮できますが、コールドスタート時間が長くなります",
+  "Copy": "コピー",
+  "Data Preprocessing": "データ前処理",
+  "Data Preprocessing Path": "データ前処理パス",
+  "Data Source": "データソース",
+  "Decoder Model Config": "デコーダーモデルの構成",
+  "Decoder Model Path": "デコーダーモデルのパス",
+  "Disabled": "無効",
+  "Enable Reference Audio": "リファレンスオーディオを有効にする",
+  "English": "英語",
+  "Error Message": "エラーメッセージ",
+  "File Preprocessing": "文書前处理",
+  "Generate": "生成",
+  "Generated Audio": "生成されたオーディオ",
+  "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format": "音声に対応するテキストがない場合は、ASRを適用してサポートします。.txtまたは.lab形式をサポートしています",
+  "Infer interface is closed": "推論インターフェースが閉じられています",
+  "Inference Configuration": "推論設定",
+  "Inference Server Configuration": "推論サーバー設定",
+  "Inference Server Error": "推論サーバーエラー",
+  "Inferring interface is launched at {}": "推論インターフェースが{}で起動しました",
+  "Initial Learning Rate": "初期学習率",
+  "Input Audio & Source Path for Transcription": "入力オーディオと文字起こしのソースパス",
+  "Input Text": "入力テキスト",
+  "Invalid path: {}": "無効なパス: {}",
+  "It is recommended to use CUDA, if you have low configuration, use CPU": "CUDAの使用をお勧めします。低い構成の場合はCPUを使用してください",
+  "Iterative Prompt Length, 0 means off": "反復プロンプト長。0はオフを意味します",
+  "Japanese": "日本語",
+  "LLAMA Configuration": "LLAMA設定",
+  "LLAMA Model Config": "LLAMAモデル設定",
+  "LLAMA Model Path": "LLAMAモデルパス",
+  "Labeling Device": "ラベリングデバイス",
+  "LoRA Model to be merged": "マージするLoRAモデル",
+  "Maximum Audio Duration": "最大オーディオの長さ",
+  "Maximum Length per Sample": "サンプルあたりの最大長",
+  "Maximum Training Steps": "最大トレーニングステップ数",
+  "Maximum tokens per batch, 0 means no limit": "バッチあたりの最大トークン数。0は制限なしを意味します",
+  "Merge": "マージ",
+  "Merge LoRA": "LoRAのマージ",
+  "Merge successfully": "マージに成功しました",
+  "Minimum Audio Duration": "最小オーディオの長さ",
+  "Model Output Path": "モデル出力パス",
+  "Model Size": "モデルサイズ",
+  "Move": "移動",
+  "Move files successfully": "ファイルの移動に成功しました",
+  "No audio generated, please check the input text.": "オーディオが生成されていません。入力テキストを確認してください。",
+  "No selected options": "選択されたオプションはありません",
+  "Number of Workers": "ワーカー数",
+  "Open Inference Server": "推論サーバーを開く",
+  "Open Labeler WebUI": "ラベラーWebUIを開く",
+  "Open Tensorboard": "Tensorboardを開く",
+  "Opened labeler in browser": "ブラウザでラベラーを開きました",
+  "Optional Label Language": "オプションのラベル言語",
+  "Optional online ver": "オプションのオンラインバージョン",
+  "Output Path": "出力パス",
+  "Path error, please check the model file exists in the corresponding path": "パスエラー。対応するパスにモデルファイルが存在するか確認してください",
+  "Precision": "精度",
+  "Probability of applying Speaker Condition": "話者条件を適用する確率",
+  "Put your text here.": "ここにテキストを入力してください。",
+  "Reference Audio": "リファレンスオーディオ",
+  "Reference Text": "リファレンステキスト",
+  "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "関連コードはBSD-3-Clauseライセンスの下でリリースされ、重みはCC BY-NC-SA 4.0ライセンスの下でリリースされます。",
+  "Remove Selected Data": "選択したデータを削除",
+  "Removed path successfully!": "パスの削除に成功しました！",
+  "Repetition Penalty": "反復ペナルティ",
+  "Save model every n steps": "nステップごとにモデルを保存",
+  "Select LLAMA ckpt": " LLAMA チェックポイントを選択",
+  "Select VITS ckpt": "VITS チェックポイントを選択",
+  "Select VQGAN ckpt": "VQGAN チェックポイントを選択",
+  "Select source file processing method": "ソースファイルの処理方法を選択",
+  "Select the model to be trained (Depending on the Tab page you are on)": "タブページに応じてトレーニングするモデルを選択してください",
+  "Selected: {}": "選択済み: {}",
+  "Speaker": "話者",
+  "Speaker is identified by the folder name": "話者はフォルダ名で識別されます",
+  "Start Training": "トレーニング開始",
+  "Streaming Audio": "ストリーミングオーディオ",
+  "Streaming Generate": "ストリーミング合成",
+  "Tensorboard Host": "Tensorboardホスト",
+  "Tensorboard Log Path": "Tensorboardログパス",
+  "Tensorboard Port": "Tensorboardポート",
+  "Tensorboard interface is closed": "Tensorboardインターフェースが閉じられています",
+  "Tensorboard interface is launched at {}": "Tensorboardインターフェースが{}で起動されました",
+  "Text is too long, please keep it under {} characters.": "テキストが長すぎます。{}文字以内に抑えてください。",
+  "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.": "左側の入力フォルダまたはファイルリストのパス。チェックの有無にかかわらず、このリストの後続のトレーニングに使用されます。",
+  "Training Configuration": "トレーニング設定",
+  "Training Error": "トレーニングエラー",
+  "Training stopped": "トレーニングが停止しました",
+  "Type name of the speaker": "話者の名前を入力",
+  "Type the path or select from the dropdown": "パスを入力するか、ドロップダウンから選択してください",
+  "Use LoRA": "LoRAを使用",
+  "Use LoRA can save GPU memory, but may reduce the quality of the model": "LoRAを使用するとGPUメモリを節約できますが、モデルの品質が低下する可能性があります",
+  "Use filelist": "ファイルリストを使用",
+  "Use large for 10G+ GPU, medium for 5G, small for 2G": "10G以上のGPUには大、5Gには中、2Gには小を使用してください",
+  "VITS Configuration": "VITS の構成",
+  "VQGAN Configuration": "VQGAN の構成",
+  "Validation Batch Size": "検証バッチサイズ",
+  "View the status of the preprocessing folder (use the slider to control the depth of the tree)": "前処理フォルダの状態を表示（スライダーを使用してツリーの深さを制御）",
+  "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.": "モデルの誤用については一切責任を負いません。使用する前に、現地の法律と規制を考慮してください。",
+  "WebUI Host": "WebUIホスト",
+  "WebUI Port": "WebUIポート",
+  "Whisper Model": "Whisperモデル",
+  "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).": "ソースコードは[こちら](https://github.com/fishaudio/fish-speech)、モデルは[こちら](https://huggingface.co/fishaudio/fish-speech-1)にあります。",
+  "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU": "30シリーズ以降のGPUにはbf16-trueを、10シリーズ以降のGPUには16-mixedをお勧めします",
+  "latest": "最新",
+  "new": "新規",
+  "Realtime Transform Text": "リアルタイム変換テキスト",
+  "Normalization Result Preview (Currently Only Chinese)": "正規化結果プレビュー（現在は中国語のみ）",
+  "Text Normalization": "テキスト正規化"
+
 }

fish_speech/i18n/locale/zh_CN.json

@@ -1,119 +1,122 @@
 {
-    "16-mixed is recommended for 10+ series GPU": "10+ 系列 GPU 建议使用 16-mixed",
-    "5 to 10 seconds of reference audio, useful for specifying speaker.": "5 到 10 秒的参考音频，适用于指定音色。",
-    "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).": "由 [Fish Audio](https://fish.audio) 研发的基于 VQ-GAN 和 Llama 的多语种语音合成.",
-    "Accumulate Gradient Batches": "梯度累积批次",
-    "Add to Processing Area": "加入处理区",
-    "Added path successfully!": "添加路径成功!",
-    "Advanced Config": "高级参数",
-    "Base LLAMA Model": "基础 LLAMA 模型",
-    "Batch Inference": "批量推理",
-    "Batch Size": "批次大小",
-    "Changing with the Model Path": "随模型路径变化",
-    "Chinese": "中文",
-    "Compile Model": "编译模型",
-    "Compile the model can significantly reduce the inference time, but will increase cold start time": "编译模型可以显著减少推理时间，但会增加冷启动时间",
-    "Copy": "复制",
-    "Data Preprocessing": "数据预处理",
-    "Data Preprocessing Path": "数据预处理路径",
-    "Data Source": "数据源",
-    "Decoder Model Config": "解码器模型配置",
-    "Decoder Model Path": "解码器模型路径",
-    "Disabled": "禁用",
-    "Enable Reference Audio": "启用参考音频",
-    "English": "英文",
-    "Error Message": "错误信息",
-    "File Preprocessing": "文件预处理",
-    "Generate": "生成",
-    "Generated Audio": "音频",
-    "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format": "如果音频没有对应的文本，可以应用 ASR 辅助，支持 .txt 或 .lab 格式",
-    "Infer interface is closed": "推理界面已关闭",
-    "Inference Configuration": "推理配置",
-    "Inference Server Configuration": "推理服务器配置",
-    "Inference Server Error": "推理服务器错误",
-    "Inferring interface is launched at {}": "推理界面已在 {} 上启动",
-    "Initial Learning Rate": "初始学习率",
-    "Input Audio & Source Path for Transcription": "输入音频和转录源路径",
-    "Input Text": "输入文本",
-    "Invalid path: {}": "无效路径: {}",
-    "It is recommended to use CUDA, if you have low configuration, use CPU": "建议使用 CUDA，如果配置较低，使用 CPU",
-    "Iterative Prompt Length, 0 means off": "迭代提示长度，0 表示关闭",
-    "Japanese": "日文",
-    "LLAMA Configuration": "LLAMA 配置",
-    "LLAMA Model Config": "LLAMA 模型配置",
-    "LLAMA Model Path": "LLAMA 模型路径",
-    "Labeling Device": "标注加速设备",
-    "LoRA Model to be merged": "要合并的 LoRA 模型",
-    "Maximum Audio Duration": "最大音频时长",
-    "Maximum Length per Sample": "每个样本的最大长度",
-    "Maximum Training Steps": "最大训练步数",
-    "Maximum tokens per batch, 0 means no limit": "每批最大令牌数，0 表示无限制",
-    "Merge": "合并",
-    "Merge LoRA": "合并 LoRA",
-    "Merge successfully": "合并成功",
-    "Minimum Audio Duration": "最小音频时长",
-    "Model Output Path": "模型输出路径",
-    "Model Size": "模型规模",
-    "Move": "移动",
-    "Move files successfully": "移动文件成功",
-    "No audio generated, please check the input text.": "没有生成音频，请检查输入文本.",
-    "No selected options": "没有选择的选项",
-    "Number of Workers": "数据加载进程数",
-    "Open Inference Server": "打开推理服务器",
-    "Open Labeler WebUI": "打开标注工具",
-    "Open Tensorboard": "打开 Tensorboard",
-    "Opened labeler in browser": "在浏览器中打开标注工具",
-    "Optional Label Language": "[可选] 标注语言",
-    "Optional online ver": "[可选] 使用在线版",
-    "Output Path": "输出路径",
-    "Path error, please check the model file exists in the corresponding path": "路径错误，请检查模型文件是否存在于相应路径",
-    "Precision": "精度",
-    "Probability of applying Speaker Condition": "应用说话人条件的概率",
-    "Put your text here.": "在此处输入文本.",
-    "Reference Audio": "参考音频",
-    "Reference Text": "参考文本",
-    "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "相关代码使用 BSD-3-Clause 许可证发布，权重使用 CC BY-NC-SA 4.0 许可证发布.",
-    "Remove Selected Data": "移除选中数据",
-    "Removed path successfully!": "移除路径成功!",
-    "Repetition Penalty": "重复惩罚",
-    "Save model every n steps": "每 n 步保存模型",
-    "Select LLAMA ckpt": "选择 LLAMA 检查点",
-    "Select VITS ckpt": "选择 VITS 检查点",
-    "Select VQGAN ckpt": "选择 VQGAN 检查点",
-    "Select source file processing method": "选择源文件处理方法",
-    "Select the model to be trained (Depending on the Tab page you are on)": "根据您所在的选项卡页面选择要训练的模型",
-    "Selected: {}": "已选择: {}",
-    "Speaker": "说话人",
-    "Speaker is identified by the folder name": "自动根据父目录名称识别说话人",
-    "Start Training": "开始训练",
-    "Streaming Audio": "流式音频",
-    "Streaming Generate": "流式合成",
-    "Tensorboard Host": "Tensorboard 监听地址",
-    "Tensorboard Log Path": "Tensorboard 日志路径",
-    "Tensorboard Port": "Tensorboard 端口",
-    "Tensorboard interface is closed": "Tensorboard 界面已关闭",
-    "Tensorboard interface is launched at {}": "Tensorboard 界面已在 {} 上启动",
-    "Text is too long, please keep it under {} characters.": "文本太长，请保持在 {} 个字符以内.",
-    "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.": "左侧输入文件夹的路径或文件列表。无论是否选中，都将在此列表中用于后续训练.",
-    "Training Configuration": "训练配置",
-    "Training Error": "训练错误",
-    "Training stopped": "训练已停止",
-    "Type name of the speaker": "输入说话人的名称",
-    "Type the path or select from the dropdown": "输入路径或从下拉菜单中选择",
-    "Use LoRA": "使用 LoRA",
-    "Use LoRA can save GPU memory, but may reduce the quality of the model": "使用 LoRA 可以节省 GPU 内存，但可能会降低模型质量",
-    "Use filelist": "使用文件列表",
-    "Use large for 10G+ GPU, medium for 5G, small for 2G": "10G+ GPU 使用 large, 5G 使用 medium, 2G 使用 small",
-    "VITS Configuration": "VITS 配置",
-    "VQGAN Configuration": "VQGAN 配置",
-    "Validation Batch Size": "验证批次大小",
-    "View the status of the preprocessing folder (use the slider to control the depth of the tree)": "查看预处理文件夹的状态 (使用滑块控制树的深度)",
-    "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.": "我们不对模型的任何滥用负责，请在使用之前考虑您当地的法律法规.",
-    "WebUI Host": "WebUI 监听地址",
-    "WebUI Port": "WebUI 端口",
-    "Whisper Model": "Whisper 模型",
-    "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).": "你可以在 [这里](https://github.com/fishaudio/fish-speech) 找到源代码和 [这里](https://huggingface.co/fishaudio/fish-speech-1) 找到模型.",
-    "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU": "30+ 系列 GPU 建议使用 bf16-true, 10+ 系列 GPU 建议使用 16-mixed",
-    "latest": "最近的检查点",
-    "new": "创建新的检查点"
+  "16-mixed is recommended for 10+ series GPU": "10+ 系列 GPU 建议使用 16-mixed",
+  "5 to 10 seconds of reference audio, useful for specifying speaker.": "5 到 10 秒的参考音频，适用于指定音色。",
+  "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).": "由 [Fish Audio](https://fish.audio) 研发的基于 VQ-GAN 和 Llama 的多语种语音合成.",
+  "Accumulate Gradient Batches": "梯度累积批次",
+  "Add to Processing Area": "加入处理区",
+  "Added path successfully!": "添加路径成功!",
+  "Advanced Config": "高级参数",
+  "Base LLAMA Model": "基础 LLAMA 模型",
+  "Batch Inference": "批量推理",
+  "Batch Size": "批次大小",
+  "Changing with the Model Path": "随模型路径变化",
+  "Chinese": "中文",
+  "Compile Model": "编译模型",
+  "Compile the model can significantly reduce the inference time, but will increase cold start time": "编译模型可以显著减少推理时间，但会增加冷启动时间",
+  "Copy": "复制",
+  "Data Preprocessing": "数据预处理",
+  "Data Preprocessing Path": "数据预处理路径",
+  "Data Source": "数据源",
+  "Decoder Model Config": "解码器模型配置",
+  "Decoder Model Path": "解码器模型路径",
+  "Disabled": "禁用",
+  "Enable Reference Audio": "启用参考音频",
+  "English": "英文",
+  "Error Message": "错误信息",
+  "File Preprocessing": "文件预处理",
+  "Generate": "生成",
+  "Generated Audio": "音频",
+  "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format": "如果音频没有对应的文本，可以应用 ASR 辅助，支持 .txt 或 .lab 格式",
+  "Infer interface is closed": "推理界面已关闭",
+  "Inference Configuration": "推理配置",
+  "Inference Server Configuration": "推理服务器配置",
+  "Inference Server Error": "推理服务器错误",
+  "Inferring interface is launched at {}": "推理界面已在 {} 上启动",
+  "Initial Learning Rate": "初始学习率",
+  "Input Audio & Source Path for Transcription": "输入音频和转录源路径",
+  "Input Text": "输入文本",
+  "Invalid path: {}": "无效路径: {}",
+  "It is recommended to use CUDA, if you have low configuration, use CPU": "建议使用 CUDA，如果配置较低，使用 CPU",
+  "Iterative Prompt Length, 0 means off": "迭代提示长度，0 表示关闭",
+  "Japanese": "日文",
+  "LLAMA Configuration": "LLAMA 配置",
+  "LLAMA Model Config": "LLAMA 模型配置",
+  "LLAMA Model Path": "LLAMA 模型路径",
+  "Labeling Device": "标注加速设备",
+  "LoRA Model to be merged": "要合并的 LoRA 模型",
+  "Maximum Audio Duration": "最大音频时长",
+  "Maximum Length per Sample": "每个样本的最大长度",
+  "Maximum Training Steps": "最大训练步数",
+  "Maximum tokens per batch, 0 means no limit": "每批最大令牌数，0 表示无限制",
+  "Merge": "合并",
+  "Merge LoRA": "合并 LoRA",
+  "Merge successfully": "合并成功",
+  "Minimum Audio Duration": "最小音频时长",
+  "Model Output Path": "模型输出路径",
+  "Model Size": "模型规模",
+  "Move": "移动",
+  "Move files successfully": "移动文件成功",
+  "No audio generated, please check the input text.": "没有生成音频，请检查输入文本.",
+  "No selected options": "没有选择的选项",
+  "Number of Workers": "数据加载进程数",
+  "Open Inference Server": "打开推理服务器",
+  "Open Labeler WebUI": "打开标注工具",
+  "Open Tensorboard": "打开 Tensorboard",
+  "Opened labeler in browser": "在浏览器中打开标注工具",
+  "Optional Label Language": "[可选] 标注语言",
+  "Optional online ver": "[可选] 使用在线版",
+  "Output Path": "输出路径",
+  "Path error, please check the model file exists in the corresponding path": "路径错误，请检查模型文件是否存在于相应路径",
+  "Precision": "精度",
+  "Probability of applying Speaker Condition": "应用说话人条件的概率",
+  "Put your text here.": "在此处输入文本.",
+  "Reference Audio": "参考音频",
+  "Reference Text": "参考文本",
+  "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "相关代码使用 BSD-3-Clause 许可证发布，权重使用 CC BY-NC-SA 4.0 许可证发布.",
+  "Remove Selected Data": "移除选中数据",
+  "Removed path successfully!": "移除路径成功!",
+  "Repetition Penalty": "重复惩罚",
+  "Save model every n steps": "每 n 步保存模型",
+  "Select LLAMA ckpt": "选择 LLAMA 检查点",
+  "Select VITS ckpt": "选择 VITS 检查点",
+  "Select VQGAN ckpt": "选择 VQGAN 检查点",
+  "Select source file processing method": "选择源文件处理方法",
+  "Select the model to be trained (Depending on the Tab page you are on)": "根据您所在的选项卡页面选择要训练的模型",
+  "Selected: {}": "已选择: {}",
+  "Speaker": "说话人",
+  "Speaker is identified by the folder name": "自动根据父目录名称识别说话人",
+  "Start Training": "开始训练",
+  "Streaming Audio": "流式音频",
+  "Streaming Generate": "流式合成",
+  "Tensorboard Host": "Tensorboard 监听地址",
+  "Tensorboard Log Path": "Tensorboard 日志路径",
+  "Tensorboard Port": "Tensorboard 端口",
+  "Tensorboard interface is closed": "Tensorboard 界面已关闭",
+  "Tensorboard interface is launched at {}": "Tensorboard 界面已在 {} 上启动",
+  "Text is too long, please keep it under {} characters.": "文本太长，请保持在 {} 个字符以内.",
+  "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.": "左侧输入文件夹的路径或文件列表。无论是否选中，都将在此列表中用于后续训练.",
+  "Training Configuration": "训练配置",
+  "Training Error": "训练错误",
+  "Training stopped": "训练已停止",
+  "Type name of the speaker": "输入说话人的名称",
+  "Type the path or select from the dropdown": "输入路径或从下拉菜单中选择",
+  "Use LoRA": "使用 LoRA",
+  "Use LoRA can save GPU memory, but may reduce the quality of the model": "使用 LoRA 可以节省 GPU 内存，但可能会降低模型质量",
+  "Use filelist": "使用文件列表",
+  "Use large for 10G+ GPU, medium for 5G, small for 2G": "10G+ GPU 使用 large, 5G 使用 medium, 2G 使用 small",
+  "VITS Configuration": "VITS 配置",
+  "VQGAN Configuration": "VQGAN 配置",
+  "Validation Batch Size": "验证批次大小",
+  "View the status of the preprocessing folder (use the slider to control the depth of the tree)": "查看预处理文件夹的状态 (使用滑块控制树的深度)",
+  "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.": "我们不对模型的任何滥用负责，请在使用之前考虑您当地的法律法规.",
+  "WebUI Host": "WebUI 监听地址",
+  "WebUI Port": "WebUI 端口",
+  "Whisper Model": "Whisper 模型",
+  "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).": "你可以在 [这里](https://github.com/fishaudio/fish-speech) 找到源代码和 [这里](https://huggingface.co/fishaudio/fish-speech-1) 找到模型.",
+  "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU": "30+ 系列 GPU 建议使用 bf16-true, 10+ 系列 GPU 建议使用 16-mixed",
+  "latest": "最近的检查点",
+  "new": "创建新的检查点",
+  "Realtime Transform Text": "实时规范化文本",
+  "Normalization Result Preview (Currently Only Chinese)": "规范化结果预览",
+  "Text Normalization": "文本规范化"
 }

fish_speech/text/chn_text_norm/.gitignore

@@ -0,0 +1,114 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+# JetBrains PyCharm
+.idea
+
+# Customize
+references
+url.txt
+
+# Git
+.git

fish_speech/text/chn_text_norm/README.md

@@ -0,0 +1,36 @@
+# This account is no longer in use, see [Atomicoo](https://github.com/atomicoo) for my latest works.
+
+# Chn Text Norm
+
+this is a repository for chinese text normalization (no longer maintained).
+
+## Quick Start ##
+
+### Git Clone Repo ###
+
+git clone this repo to the root directory of your project which need to use it.
+
+    cd /path/to/proj
+    git clone https://github.com/Joee1995/chn-text-norm.git
+
+after that, your doc tree should be:
+```
+proj                     # root of your project
+|--- chn_text_norm       # this chn-text-norm tool
+     |--- text.py
+     |--- ...
+|--- text_normalize.py   # your text normalization code
+|--- ...
+```
+
+### How to Use ? ###
+
+    # text_normalize.py
+    from chn_text_norm.text import *
+    
+    raw_text = 'your raw text'
+    text = Text(raw_text=raw_text).normalize()
+
+### How to add quantums ###
+
+打开test.py，然后你就知道怎么做了。

fish_speech/text/chn_text_norm/basic_class.py

@@ -0,0 +1,172 @@
+# -*- coding: utf-8 -*-
+"""基本类
+中文字符类
+中文数字/数位类
+中文数字类
+中文数位类
+中文数字系统类
+中文数学符号类
+*中文其他符号类
+"""
+
+__author__ = "Zhiyang Zhou <zyzhou@stu.xmu.edu.cn>"
+__data__ = "2019-05-02"
+
+from fish_speech.text.chn_text_norm.basic_constant import NUMBERING_TYPES
+
+
+class ChineseChar(object):
+    """
+    中文字符
+    每个字符对应简体和繁体,
+    e.g. 简体 = '负', 繁体 = '負'
+    转换时可转换为简体或繁体
+    """
+
+    def __init__(self, simplified, traditional):
+        self.simplified = simplified
+        self.traditional = traditional
+        self.__repr__ = self.__str__
+
+    def __str__(self):
+        return self.simplified or self.traditional or None
+
+    def __repr__(self):
+        return self.__str__()
+
+
+class ChineseNumberUnit(ChineseChar):
+    """
+    中文数字/数位字符
+    每个字符除繁简体外还有一个额外的大写字符
+    e.g. '陆' 和 '陸'
+    """
+
+    def __init__(self, power, simplified, traditional, big_s, big_t):
+        super(ChineseNumberUnit, self).__init__(simplified, traditional)
+        self.power = power
+        self.big_s = big_s
+        self.big_t = big_t
+
+    def __str__(self):
+        return "10^{}".format(self.power)
+
+    @classmethod
+    def create(cls, index, value, numbering_type=NUMBERING_TYPES[1], small_unit=False):
+
+        if small_unit:
+            return ChineseNumberUnit(
+                power=index + 1,
+                simplified=value[0],
+                traditional=value[1],
+                big_s=value[1],
+                big_t=value[1],
+            )
+        elif numbering_type == NUMBERING_TYPES[0]:
+            return ChineseNumberUnit(
+                power=index + 8,
+                simplified=value[0],
+                traditional=value[1],
+                big_s=value[0],
+                big_t=value[1],
+            )
+        elif numbering_type == NUMBERING_TYPES[1]:
+            return ChineseNumberUnit(
+                power=(index + 2) * 4,
+                simplified=value[0],
+                traditional=value[1],
+                big_s=value[0],
+                big_t=value[1],
+            )
+        elif numbering_type == NUMBERING_TYPES[2]:
+            return ChineseNumberUnit(
+                power=pow(2, index + 3),
+                simplified=value[0],
+                traditional=value[1],
+                big_s=value[0],
+                big_t=value[1],
+            )
+        else:
+            raise ValueError(
+                "Counting type should be in {0} ({1} provided).".format(
+                    NUMBERING_TYPES, numbering_type
+                )
+            )
+
+
+class ChineseNumberDigit(ChineseChar):
+    """
+    中文数字字符
+    """
+
+    def __init__(
+        self, value, simplified, traditional, big_s, big_t, alt_s=None, alt_t=None
+    ):
+        super(ChineseNumberDigit, self).__init__(simplified, traditional)
+        self.value = value
+        self.big_s = big_s
+        self.big_t = big_t
+        self.alt_s = alt_s
+        self.alt_t = alt_t
+
+    def __str__(self):
+        return str(self.value)
+
+    @classmethod
+    def create(cls, i, v):
+        return ChineseNumberDigit(i, v[0], v[1], v[2], v[3])
+
+
+class ChineseMath(ChineseChar):
+    """
+    中文数位字符
+    """
+
+    def __init__(self, simplified, traditional, symbol, expression=None):
+        super(ChineseMath, self).__init__(simplified, traditional)
+        self.symbol = symbol
+        self.expression = expression
+        self.big_s = simplified
+        self.big_t = traditional
+
+
+CC, CNU, CND, CM = ChineseChar, ChineseNumberUnit, ChineseNumberDigit, ChineseMath
+
+
+class NumberSystem(object):
+    """
+    中文数字系统
+    """
+
+    pass
+
+
+class MathSymbol(object):
+    """
+    用于中文数字系统的数学符号 (繁/简体), e.g.
+    positive = ['正', '正']
+    negative = ['负', '負']
+    point = ['点', '點']
+    """
+
+    def __init__(self, positive, negative, point):
+        self.positive = positive
+        self.negative = negative
+        self.point = point
+
+    def __iter__(self):
+        for v in self.__dict__.values():
+            yield v
+
+
+# class OtherSymbol(object):
+#     """
+#     其他符号
+#     """
+#
+#     def __init__(self, sil):
+#         self.sil = sil
+#
+#     def __iter__(self):
+#         for v in self.__dict__.values():
+#             yield v

fish_speech/text/chn_text_norm/basic_constant.py

@@ -0,0 +1,30 @@
+# -*- coding: utf-8 -*-
+"""基本常量
+中文数字/数位/符号字符常量
+"""
+
+__author__ = "Zhiyang Zhou <zyzhou@stu.xmu.edu.cn>"
+__data__ = "2019-05-02"
+
+CHINESE_DIGIS = "零一二三四五六七八九"
+BIG_CHINESE_DIGIS_SIMPLIFIED = "零壹贰叁肆伍陆柒捌玖"
+BIG_CHINESE_DIGIS_TRADITIONAL = "零壹貳參肆伍陸柒捌玖"
+SMALLER_BIG_CHINESE_UNITS_SIMPLIFIED = "十百千万"
+SMALLER_BIG_CHINESE_UNITS_TRADITIONAL = "拾佰仟萬"
+LARGER_CHINESE_NUMERING_UNITS_SIMPLIFIED = "亿兆京垓秭穰沟涧正载"
+LARGER_CHINESE_NUMERING_UNITS_TRADITIONAL = "億兆京垓秭穰溝澗正載"
+SMALLER_CHINESE_NUMERING_UNITS_SIMPLIFIED = "十百千万"
+SMALLER_CHINESE_NUMERING_UNITS_TRADITIONAL = "拾佰仟萬"
+
+ZERO_ALT = "〇"
+ONE_ALT = "幺"
+TWO_ALTS = ["两", "兩"]
+
+POSITIVE = ["正", "正"]
+NEGATIVE = ["负", "負"]
+POINT = ["点", "點"]
+# PLUS = [u'加', u'加']
+# SIL = [u'杠', u'槓']
+
+# 中文数字系统类型
+NUMBERING_TYPES = ["low", "mid", "high"]

fish_speech/text/chn_text_norm/basic_util.py

@@ -0,0 +1,342 @@
+# -*- coding: utf-8 -*-
+"""基本方法
+创建中文数字系统 方法
+中文字符串 <=> 数字串 方法
+数字串 <=> 中文字符串 方法
+"""
+
+__author__ = "Zhiyang Zhou <zyzhou@stu.xmu.edu.cn>"
+__data__ = "2019-05-02"
+
+from fish_speech.text.chn_text_norm.basic_class import *
+from fish_speech.text.chn_text_norm.basic_constant import *
+
+
+def create_system(numbering_type=NUMBERING_TYPES[1]):
+    """
+    根据数字系统类型返回创建相应的数字系统，默认为 mid
+    NUMBERING_TYPES = ['low', 'mid', 'high']: 中文数字系统类型
+        low:  '兆' = '亿' * '十' = $10^{9}$,  '京' = '兆' * '十', etc.
+        mid:  '兆' = '亿' * '万' = $10^{12}$, '京' = '兆' * '万', etc.
+        high: '兆' = '亿' * '亿' = $10^{16}$, '京' = '兆' * '兆', etc.
+    返回对应的数字系统
+    """
+
+    # chinese number units of '亿' and larger
+    all_larger_units = zip(
+        LARGER_CHINESE_NUMERING_UNITS_SIMPLIFIED,
+        LARGER_CHINESE_NUMERING_UNITS_TRADITIONAL,
+    )
+    larger_units = [
+        CNU.create(i, v, numbering_type, False) for i, v in enumerate(all_larger_units)
+    ]
+    # chinese number units of '十, 百, 千, 万'
+    all_smaller_units = zip(
+        SMALLER_CHINESE_NUMERING_UNITS_SIMPLIFIED,
+        SMALLER_CHINESE_NUMERING_UNITS_TRADITIONAL,
+    )
+    smaller_units = [
+        CNU.create(i, v, small_unit=True) for i, v in enumerate(all_smaller_units)
+    ]
+    # digis
+    chinese_digis = zip(
+        CHINESE_DIGIS,
+        CHINESE_DIGIS,
+        BIG_CHINESE_DIGIS_SIMPLIFIED,
+        BIG_CHINESE_DIGIS_TRADITIONAL,
+    )
+    digits = [CND.create(i, v) for i, v in enumerate(chinese_digis)]
+    digits[0].alt_s, digits[0].alt_t = ZERO_ALT, ZERO_ALT
+    digits[1].alt_s, digits[1].alt_t = ONE_ALT, ONE_ALT
+    digits[2].alt_s, digits[2].alt_t = TWO_ALTS[0], TWO_ALTS[1]
+
+    # symbols
+    positive_cn = CM(POSITIVE[0], POSITIVE[1], "+", lambda x: x)
+    negative_cn = CM(NEGATIVE[0], NEGATIVE[1], "-", lambda x: -x)
+    point_cn = CM(POINT[0], POINT[1], ".", lambda x, y: float(str(x) + "." + str(y)))
+    # sil_cn = CM(SIL[0], SIL[1], '-', lambda x, y: float(str(x) + '-' + str(y)))
+    system = NumberSystem()
+    system.units = smaller_units + larger_units
+    system.digits = digits
+    system.math = MathSymbol(positive_cn, negative_cn, point_cn)
+    # system.symbols = OtherSymbol(sil_cn)
+    return system
+
+
+def chn2num(chinese_string, numbering_type=NUMBERING_TYPES[1]):
+
+    def get_symbol(char, system):
+        for u in system.units:
+            if char in [u.traditional, u.simplified, u.big_s, u.big_t]:
+                return u
+        for d in system.digits:
+            if char in [
+                d.traditional,
+                d.simplified,
+                d.big_s,
+                d.big_t,
+                d.alt_s,
+                d.alt_t,
+            ]:
+                return d
+        for m in system.math:
+            if char in [m.traditional, m.simplified]:
+                return m
+
+    def string2symbols(chinese_string, system):
+        int_string, dec_string = chinese_string, ""
+        for p in [system.math.point.simplified, system.math.point.traditional]:
+            if p in chinese_string:
+                int_string, dec_string = chinese_string.split(p)
+                break
+        return [get_symbol(c, system) for c in int_string], [
+            get_symbol(c, system) for c in dec_string
+        ]
+
+    def correct_symbols(integer_symbols, system):
+        """
+        一百八 to 一百八十
+        一亿一千三百万 to 一亿 一千万 三百万
+        """
+
+        if integer_symbols and isinstance(integer_symbols[0], CNU):
+            if integer_symbols[0].power == 1:
+                integer_symbols = [system.digits[1]] + integer_symbols
+
+        if len(integer_symbols) > 1:
+            if isinstance(integer_symbols[-1], CND) and isinstance(
+                integer_symbols[-2], CNU
+            ):
+                integer_symbols.append(
+                    CNU(integer_symbols[-2].power - 1, None, None, None, None)
+                )
+
+        result = []
+        unit_count = 0
+        for s in integer_symbols:
+            if isinstance(s, CND):
+                result.append(s)
+                unit_count = 0
+            elif isinstance(s, CNU):
+                current_unit = CNU(s.power, None, None, None, None)
+                unit_count += 1
+
+            if unit_count == 1:
+                result.append(current_unit)
+            elif unit_count > 1:
+                for i in range(len(result)):
+                    if (
+                        isinstance(result[-i - 1], CNU)
+                        and result[-i - 1].power < current_unit.power
+                    ):
+                        result[-i - 1] = CNU(
+                            result[-i - 1].power + current_unit.power,
+                            None,
+                            None,
+                            None,
+                            None,
+                        )
+        return result
+
+    def compute_value(integer_symbols):
+        """
+        Compute the value.
+        When current unit is larger than previous unit, current unit * all previous units will be used as all previous units.
+        e.g. '两千万' = 2000 * 10000 not 2000 + 10000
+        """
+        value = [0]
+        last_power = 0
+        for s in integer_symbols:
+            if isinstance(s, CND):
+                value[-1] = s.value
+            elif isinstance(s, CNU):
+                value[-1] *= pow(10, s.power)
+                if s.power > last_power:
+                    value[:-1] = list(map(lambda v: v * pow(10, s.power), value[:-1]))
+                    last_power = s.power
+                value.append(0)
+        return sum(value)
+
+    system = create_system(numbering_type)
+    int_part, dec_part = string2symbols(chinese_string, system)
+    int_part = correct_symbols(int_part, system)
+    int_str = str(compute_value(int_part))
+    dec_str = "".join([str(d.value) for d in dec_part])
+    if dec_part:
+        return "{0}.{1}".format(int_str, dec_str)
+    else:
+        return int_str
+
+
+def num2chn(
+    number_string,
+    numbering_type=NUMBERING_TYPES[1],
+    big=False,
+    traditional=False,
+    alt_zero=False,
+    alt_one=False,
+    alt_two=True,
+    use_zeros=True,
+    use_units=True,
+):
+
+    def get_value(value_string, use_zeros=True):
+
+        striped_string = value_string.lstrip("0")
+
+        # record nothing if all zeros
+        if not striped_string:
+            return []
+
+        # record one digits
+        elif len(striped_string) == 1:
+            if use_zeros and len(value_string) != len(striped_string):
+                return [system.digits[0], system.digits[int(striped_string)]]
+            else:
+                return [system.digits[int(striped_string)]]
+
+        # recursively record multiple digits
+        else:
+            result_unit = next(
+                u for u in reversed(system.units) if u.power < len(striped_string)
+            )
+            result_string = value_string[: -result_unit.power]
+            return (
+                get_value(result_string)
+                + [result_unit]
+                + get_value(striped_string[-result_unit.power :])
+            )
+
+    system = create_system(numbering_type)
+
+    int_dec = number_string.split(".")
+    if len(int_dec) == 1:
+        int_string = int_dec[0]
+        dec_string = ""
+    elif len(int_dec) == 2:
+        int_string = int_dec[0]
+        dec_string = int_dec[1]
+    else:
+        raise ValueError(
+            "invalid input num string with more than one dot: {}".format(number_string)
+        )
+
+    if use_units and len(int_string) > 1:
+        result_symbols = get_value(int_string)
+    else:
+        result_symbols = [system.digits[int(c)] for c in int_string]
+    dec_symbols = [system.digits[int(c)] for c in dec_string]
+    if dec_string:
+        result_symbols += [system.math.point] + dec_symbols
+
+    if alt_two:
+        liang = CND(
+            2,
+            system.digits[2].alt_s,
+            system.digits[2].alt_t,
+            system.digits[2].big_s,
+            system.digits[2].big_t,
+        )
+        for i, v in enumerate(result_symbols):
+            if isinstance(v, CND) and v.value == 2:
+                next_symbol = (
+                    result_symbols[i + 1] if i < len(result_symbols) - 1 else None
+                )
+                previous_symbol = result_symbols[i - 1] if i > 0 else None
+                if isinstance(next_symbol, CNU) and isinstance(
+                    previous_symbol, (CNU, type(None))
+                ):
+                    if next_symbol.power != 1 and (
+                        (previous_symbol is None) or (previous_symbol.power != 1)
+                    ):
+                        result_symbols[i] = liang
+
+    # if big is True, '两' will not be used and `alt_two` has no impact on output
+    if big:
+        attr_name = "big_"
+        if traditional:
+            attr_name += "t"
+        else:
+            attr_name += "s"
+    else:
+        if traditional:
+            attr_name = "traditional"
+        else:
+            attr_name = "simplified"
+
+    result = "".join([getattr(s, attr_name) for s in result_symbols])
+
+    # if not use_zeros:
+    #     result = result.strip(getattr(system.digits[0], attr_name))
+
+    if alt_zero:
+        result = result.replace(
+            getattr(system.digits[0], attr_name), system.digits[0].alt_s
+        )
+
+    if alt_one:
+        result = result.replace(
+            getattr(system.digits[1], attr_name), system.digits[1].alt_s
+        )
+
+    for i, p in enumerate(POINT):
+        if result.startswith(p):
+            return CHINESE_DIGIS[0] + result
+
+    # ^10, 11, .., 19
+    if (
+        len(result) >= 2
+        and result[1]
+        in [
+            SMALLER_CHINESE_NUMERING_UNITS_SIMPLIFIED[0],
+            SMALLER_CHINESE_NUMERING_UNITS_TRADITIONAL[0],
+        ]
+        and result[0]
+        in [
+            CHINESE_DIGIS[1],
+            BIG_CHINESE_DIGIS_SIMPLIFIED[1],
+            BIG_CHINESE_DIGIS_TRADITIONAL[1],
+        ]
+    ):
+        result = result[1:]
+
+    return result
+
+
+if __name__ == "__main__":
+
+    # 测试程序
+    all_chinese_number_string = (
+        CHINESE_DIGIS
+        + BIG_CHINESE_DIGIS_SIMPLIFIED
+        + BIG_CHINESE_DIGIS_TRADITIONAL
+        + LARGER_CHINESE_NUMERING_UNITS_SIMPLIFIED
+        + LARGER_CHINESE_NUMERING_UNITS_TRADITIONAL
+        + SMALLER_CHINESE_NUMERING_UNITS_SIMPLIFIED
+        + SMALLER_CHINESE_NUMERING_UNITS_TRADITIONAL
+        + ZERO_ALT
+        + ONE_ALT
+        + "".join(TWO_ALTS + POSITIVE + NEGATIVE + POINT)
+    )
+
+    print("num:", chn2num("一万零四百零三点八零五"))
+    print("num:", chn2num("一亿六点三"))
+    print("num:", chn2num("一亿零六点三"))
+    print("num:", chn2num("两千零一亿六点三"))
+    # print('num:', chn2num('一零零八六'))
+    print("txt:", num2chn("10260.03", alt_zero=True))
+    print("txt:", num2chn("20037.090", numbering_type="low", traditional=True))
+    print("txt:", num2chn("100860001.77", numbering_type="high", big=True))
+    print(
+        "txt:",
+        num2chn(
+            "059523810880",
+            alt_one=True,
+            alt_two=False,
+            use_lzeros=True,
+            use_rzeros=True,
+            use_units=False,
+        ),
+    )
+
+    print(all_chinese_number_string)

fish_speech/text/chn_text_norm/cardinal.py

@@ -0,0 +1,32 @@
+# -*- coding: utf-8 -*-
+"""CARDINAL类 (包含小数DECIMAL类)
+纯数 <=> 中文字符串 方法
+中文字符串 <=> 纯数 方法
+"""
+
+__author__ = "Zhiyang Zhou <zyzhou@stu.xmu.edu.cn>"
+__data__ = "2019-05-03"
+
+from fish_speech.text.chn_text_norm.basic_util import *
+
+
+class Cardinal:
+    """
+    CARDINAL类
+    """
+
+    def __init__(self, cardinal=None, chntext=None):
+        self.cardinal = cardinal
+        self.chntext = chntext
+
+    def chntext2cardinal(self):
+        return chn2num(self.chntext)
+
+    def cardinal2chntext(self):
+        return num2chn(self.cardinal)
+
+
+if __name__ == "__main__":
+
+    # 测试程序
+    print(Cardinal(cardinal="21357.230").cardinal2chntext())

fish_speech/text/chn_text_norm/date.py

@@ -0,0 +1,75 @@
+# -*- coding: utf-8 -*-
+"""DATE类
+日期 <=> 中文字符串 方法
+中文字符串 <=> 日期 方法
+"""
+
+__author__ = "Zhiyang Zhou <zyzhou@stu.xmu.edu.cn>"
+__data__ = "2019-05-07"
+
+from fish_speech.text.chn_text_norm.cardinal import Cardinal
+from fish_speech.text.chn_text_norm.digit import Digit
+
+
+class Date:
+    """
+    DATE类
+    """
+
+    def __init__(self, date=None, chntext=None):
+        self.date = date
+        self.chntext = chntext
+
+    # def chntext2date(self):
+    #     chntext = self.chntext
+    #     try:
+    #         year, other = chntext.strip().split('年', maxsplit=1)
+    #         year = Digit(chntext=year).digit2chntext() + '年'
+    #     except ValueError:
+    #         other = chntext
+    #         year = ''
+    #     if other:
+    #         try:
+    #             month, day = other.strip().split('月', maxsplit=1)
+    #             month = Cardinal(chntext=month).chntext2cardinal() + '月'
+    #         except ValueError:
+    #             day = chntext
+    #             month = ''
+    #         if day:
+    #             day = Cardinal(chntext=day[:-1]).chntext2cardinal() + day[-1]
+    #     else:
+    #         month = ''
+    #         day = ''
+    #     date = year + month + day
+    #     self.date = date
+    #     return self.date
+
+    def date2chntext(self):
+        date = self.date
+        try:
+            year, other = date.strip().split("年", maxsplit=1)
+            year = Digit(digit=year).digit2chntext() + "年"
+        except ValueError:
+            other = date
+            year = ""
+        if other:
+            try:
+                month, day = other.strip().split("月", maxsplit=1)
+                month = Cardinal(cardinal=month).cardinal2chntext() + "月"
+            except ValueError:
+                day = date
+                month = ""
+            if day:
+                day = Cardinal(cardinal=day[:-1]).cardinal2chntext() + day[-1]
+        else:
+            month = ""
+            day = ""
+        chntext = year + month + day
+        self.chntext = chntext
+        return self.chntext
+
+
+if __name__ == "__main__":
+
+    # 测试
+    print(Date(date="09年3月16日").date2chntext())

fish_speech/text/chn_text_norm/digit.py

@@ -0,0 +1,32 @@
+# -*- coding: utf-8 -*-
+"""DIGIT类
+数字串 <=> 中文字符串 方法
+中文字符串 <=> 数字串 方法
+"""
+
+__author__ = "Zhiyang Zhou <zyzhou@stu.xmu.edu.cn>"
+__data__ = "2019-05-03"
+
+from fish_speech.text.chn_text_norm.basic_util import *
+
+
+class Digit:
+    """
+    DIGIT类
+    """
+
+    def __init__(self, digit=None, chntext=None):
+        self.digit = digit
+        self.chntext = chntext
+
+    # def chntext2digit(self):
+    #     return chn2num(self.chntext)
+
+    def digit2chntext(self):
+        return num2chn(self.digit, alt_two=False, use_units=False)
+
+
+if __name__ == "__main__":
+
+    # 测试程序
+    print(Digit(digit="2016").digit2chntext())

fish_speech/text/chn_text_norm/fraction.py

@@ -0,0 +1,35 @@
+# -*- coding: utf-8 -*-
+"""FRACTION类
+分数 <=> 中文字符串 方法
+中文字符串 <=> 分数 方法
+"""
+
+__author__ = "Zhiyang Zhou <zyzhou@stu.xmu.edu.cn>"
+__data__ = "2019-05-03"
+
+from fish_speech.text.chn_text_norm.basic_util import *
+
+
+class Fraction:
+    """
+    FRACTION类
+    """
+
+    def __init__(self, fraction=None, chntext=None):
+        self.fraction = fraction
+        self.chntext = chntext
+
+    def chntext2fraction(self):
+        denominator, numerator = self.chntext.split("分之")
+        return chn2num(numerator) + "/" + chn2num(denominator)
+
+    def fraction2chntext(self):
+        numerator, denominator = self.fraction.split("/")
+        return num2chn(denominator) + "分之" + num2chn(numerator)
+
+
+if __name__ == "__main__":
+
+    # 测试程序
+    print(Fraction(fraction="2135/7230").fraction2chntext())
+    print(Fraction(chntext="五百八十一分之三百六十九").chntext2fraction())

fish_speech/text/chn_text_norm/money.py

@@ -0,0 +1,43 @@
+# -*- coding: utf-8 -*-
+"""MONEY类
+金钱 <=> 中文字符串 方法
+中文字符串 <=> 金钱 方法
+"""
+import re
+
+__author__ = "Zhiyang Zhou <zyzhou@stu.xmu.edu.cn>"
+__data__ = "2019-05-08"
+
+from fish_speech.text.chn_text_norm.cardinal import Cardinal
+
+
+class Money:
+    """
+    MONEY类
+    """
+
+    def __init__(self, money=None, chntext=None):
+        self.money = money
+        self.chntext = chntext
+
+    # def chntext2money(self):
+    #     return self.money
+
+    def money2chntext(self):
+        money = self.money
+        pattern = re.compile(r"(\d+(\.\d+)?)")
+        matchers = pattern.findall(money)
+        if matchers:
+            for matcher in matchers:
+                money = money.replace(
+                    matcher[0], Cardinal(cardinal=matcher[0]).cardinal2chntext()
+                )
+        self.chntext = money
+        return self.chntext
+
+
+if __name__ == "__main__":
+
+    # 测试
+    print(Money(money="21.5万元").money2chntext())
+    print(Money(money="230块5毛").money2chntext())

fish_speech/text/chn_text_norm/percentage.py

@@ -0,0 +1,33 @@
+# -*- coding: utf-8 -*-
+"""PERCENTAGE类
+百分数 <=> 中文字符串 方法
+中文字符串 <=> 百分数 方法
+"""
+
+__author__ = "Zhiyang Zhou <zyzhou@stu.xmu.edu.cn>"
+__data__ = "2019-05-06"
+
+from fish_speech.text.chn_text_norm.basic_util import *
+
+
+class Percentage:
+    """
+    PERCENTAGE类
+    """
+
+    def __init__(self, percentage=None, chntext=None):
+        self.percentage = percentage
+        self.chntext = chntext
+
+    def chntext2percentage(self):
+        return chn2num(self.chntext.strip().strip("百分之")) + "%"
+
+    def percentage2chntext(self):
+        return "百分之" + num2chn(self.percentage.strip().strip("%"))
+
+
+if __name__ == "__main__":
+
+    # 测试程序
+    print(Percentage(chntext="百分之五十六点零三").chntext2percentage())
+    print(Percentage(percentage="65.3%").percentage2chntext())

fish_speech/text/chn_text_norm/telephone.py

@@ -0,0 +1,51 @@
+# -*- coding: utf-8 -*-
+"""TELEPHONE类
+电话号码 <=> 中文字符串 方法
+中文字符串 <=> 电话号码 方法
+"""
+
+__author__ = "Zhiyang Zhou <zyzhou@stu.xmu.edu.cn>"
+__data__ = "2019-05-03"
+
+from fish_speech.text.chn_text_norm.basic_util import *
+
+
+class TelePhone:
+    """
+    TELEPHONE类
+    """
+
+    def __init__(self, telephone=None, raw_chntext=None, chntext=None):
+        self.telephone = telephone
+        self.raw_chntext = raw_chntext
+        self.chntext = chntext
+
+    # def chntext2telephone(self):
+    #     sil_parts = self.raw_chntext.split('<SIL>')
+    #     self.telephone = '-'.join([
+    #         str(chn2num(p)) for p in sil_parts
+    #     ])
+    #     return self.telephone
+
+    def telephone2chntext(self, fixed=False):
+
+        if fixed:
+            sil_parts = self.telephone.split("-")
+            self.raw_chntext = "<SIL>".join(
+                [num2chn(part, alt_two=False, use_units=False) for part in sil_parts]
+            )
+            self.chntext = self.raw_chntext.replace("<SIL>", "")
+        else:
+            sp_parts = self.telephone.strip("+").split()
+            self.raw_chntext = "<SP>".join(
+                [num2chn(part, alt_two=False, use_units=False) for part in sp_parts]
+            )
+            self.chntext = self.raw_chntext.replace("<SP>", "")
+        return self.chntext
+
+
+if __name__ == "__main__":
+
+    # 测试程序
+    print(TelePhone(telephone="0595-23980880").telephone2chntext())
+    # print(TelePhone(raw_chntext='零五九五杠二三八六五零九八').chntext2telephone())

fish_speech/text/chn_text_norm/text.py

@@ -0,0 +1,177 @@
+# -*- coding: utf-8 -*-
+"""
+TEXT类
+"""
+
+__author__ = "Zhiyang Zhou <zyzhou@stu.xmu.edu.cn>"
+__data__ = "2019-05-03"
+
+import re
+
+from fish_speech.text.chn_text_norm.cardinal import Cardinal
+from fish_speech.text.chn_text_norm.date import Date
+from fish_speech.text.chn_text_norm.digit import Digit
+from fish_speech.text.chn_text_norm.fraction import Fraction
+from fish_speech.text.chn_text_norm.money import Money
+from fish_speech.text.chn_text_norm.percentage import Percentage
+from fish_speech.text.chn_text_norm.telephone import TelePhone
+
+CURRENCY_NAMES = (
+    "(人民币|美元|日元|英镑|欧元|马克|法郎|加拿大元|澳元|港币|先令|芬兰马克|爱尔兰镑|"
+    "里拉|荷兰盾|埃斯库多|比塞塔|印尼盾|林吉特|新西兰元|比索|卢布|新加坡元|韩元|泰铢)"
+)
+CURRENCY_UNITS = "((亿|千万|百万|万|千|百)|(亿|千万|百万|万|千|百|)元|(亿|千万|百万|万|千|百|)块|角|毛|分)"
+COM_QUANTIFIERS = (
+    "(匹|张|座|回|场|尾|条|个|首|阙|阵|网|炮|顶|丘|棵|只|支|袭|辆|挑|担|颗|壳|窠|曲|墙|群|腔|"
+    "砣|座|客|贯|扎|捆|刀|令|打|手|罗|坡|山|岭|江|溪|钟|队|单|双|对|出|口|头|脚|板|跳|枝|件|贴|"
+    "针|线|管|名|位|身|堂|课|本|页|家|户|层|丝|毫|厘|分|钱|两|斤|担|铢|石|钧|锱|忽|(千|毫|微)克|"
+    "毫|厘|分|寸|尺|丈|里|寻|常|铺|程|(千|分|厘|毫|微)米|撮|勺|合|升|斗|石|盘|碗|碟|叠|桶|笼|盆|"
+    "盒|杯|钟|斛|锅|簋|篮|盘|桶|罐|瓶|壶|卮|盏|箩|箱|煲|啖|袋|钵|年|月|日|季|刻|时|周|天|秒|分|旬|"
+    "纪|岁|世|更|夜|春|夏|秋|冬|代|伏|辈|丸|泡|粒|颗|幢|堆|条|根|支|道|面|片|张|颗|块|人|抽)"
+)
+
+
+class Text:
+    """
+    Text类
+    """
+
+    def __init__(self, raw_text, norm_text=None):
+        self.raw_text = "^" + raw_text + "$"
+        self.norm_text = norm_text
+
+    def _particular(self):
+        text = self.norm_text
+        pattern = re.compile(r"(([a-zA-Z]+)二([a-zA-Z]+))")
+        matchers = pattern.findall(text)
+        if matchers:
+            # print('particular')
+            for matcher in matchers:
+                text = text.replace(matcher[0], matcher[1] + "2" + matcher[2], 1)
+        self.norm_text = text
+        return self.norm_text
+
+    def normalize(self):
+        text = self.raw_text
+
+        # 规范化日期
+        pattern = re.compile(
+            r"\D+((([089]\d|(19|20)\d{2})年)?(\d{1,2}月(\d{1,2}[日号])?)?)"
+        )
+        matchers = pattern.findall(text)
+        if matchers:
+            # print('date')
+            for matcher in matchers:
+                text = text.replace(matcher[0], Date(date=matcher[0]).date2chntext(), 1)
+
+        # 规范化金钱
+        pattern = re.compile(
+            r"\D+((\d+(\.\d+)?)[多余几]?"
+            + CURRENCY_UNITS
+            + "(\d"
+            + CURRENCY_UNITS
+            + "?)?)"
+        )
+        matchers = pattern.findall(text)
+        if matchers:
+            # print('money')
+            for matcher in matchers:
+                text = text.replace(
+                    matcher[0], Money(money=matcher[0]).money2chntext(), 1
+                )
+
+        # 规范化固话/手机号码
+        # 手机
+        # http://www.jihaoba.com/news/show/13680
+        # 移动：139、138、137、136、135、134、159、158、157、150、151、152、188、187、182、183、184、178、198
+        # 联通：130、131、132、156、155、186、185、176
+        # 电信：133、153、189、180、181、177
+        pattern = re.compile(r"\D((\+?86 ?)?1([38]\d|5[0-35-9]|7[678]|9[89])\d{8})\D")
+        matchers = pattern.findall(text)
+        if matchers:
+            # print('telephone')
+            for matcher in matchers:
+                text = text.replace(
+                    matcher[0], TelePhone(telephone=matcher[0]).telephone2chntext(), 1
+                )
+        # 固话
+        pattern = re.compile(r"\D((0(10|2[1-3]|[3-9]\d{2})-?)?[1-9]\d{6,7})\D")
+        matchers = pattern.findall(text)
+        if matchers:
+            # print('fixed telephone')
+            for matcher in matchers:
+                text = text.replace(
+                    matcher[0],
+                    TelePhone(telephone=matcher[0]).telephone2chntext(fixed=True),
+                    1,
+                )
+
+        # 规范化分数
+        pattern = re.compile(r"(\d+/\d+)")
+        matchers = pattern.findall(text)
+        if matchers:
+            # print('fraction')
+            for matcher in matchers:
+                text = text.replace(
+                    matcher, Fraction(fraction=matcher).fraction2chntext(), 1
+                )
+
+        # 规范化百分数
+        text = text.replace("％", "%")
+        pattern = re.compile(r"(\d+(\.\d+)?%)")
+        matchers = pattern.findall(text)
+        if matchers:
+            # print('percentage')
+            for matcher in matchers:
+                text = text.replace(
+                    matcher[0],
+                    Percentage(percentage=matcher[0]).percentage2chntext(),
+                    1,
+                )
+
+        # 规范化纯数+量词
+        pattern = re.compile(r"(\d+(\.\d+)?)[多余几]?" + COM_QUANTIFIERS)
+        matchers = pattern.findall(text)
+        if matchers:
+            # print('cardinal+quantifier')
+            for matcher in matchers:
+                text = text.replace(
+                    matcher[0], Cardinal(cardinal=matcher[0]).cardinal2chntext(), 1
+                )
+
+        # 规范化数字编号
+        pattern = re.compile(r"(\d{4,32})")
+        matchers = pattern.findall(text)
+        if matchers:
+            # print('digit')
+            for matcher in matchers:
+                text = text.replace(matcher, Digit(digit=matcher).digit2chntext(), 1)
+
+        # 规范化纯数
+        pattern = re.compile(r"(\d+(\.\d+)?)")
+        matchers = pattern.findall(text)
+        if matchers:
+            # print('cardinal')
+            for matcher in matchers:
+                text = text.replace(
+                    matcher[0], Cardinal(cardinal=matcher[0]).cardinal2chntext(), 1
+                )
+
+        self.norm_text = text
+        self._particular()
+
+        return self.norm_text.lstrip("^").rstrip("$")
+
+
+if __name__ == "__main__":
+
+    # 测试程序
+    print(Text(raw_text="固话：0595-23865596或23880880。").normalize())
+    print(Text(raw_text="手机：+86 19859213959或15659451527。").normalize())
+    print(Text(raw_text="分数：32477/76391。").normalize())
+    print(Text(raw_text="百分数：80.03%。").normalize())
+    print(Text(raw_text="编号：31520181154418。").normalize())
+    print(Text(raw_text="纯数：2983.07克或12345.60米。").normalize())
+    print(Text(raw_text="日期：1999年2月20日或09年3月15号。").normalize())
+    print(Text(raw_text="金钱：12块5，34.5元，20.1万").normalize())
+    print(Text(raw_text="特殊：O2O或B2C。").normalize())

tools/webui.py

@@ -17,7 +17,9 @@ from transformers import AutoTokenizer
 
 pyrootutils.setup_root(__file__, indicator=".project-root", pythonpath=True)
 
+
 from fish_speech.i18n import i18n
+from fish_speech.text.chn_text_norm.text import Text as ChnNormedText
 from tools.api import decode_vq_tokens, encode_reference
 from tools.llama.generate import (
     GenerateRequest,
@@ -243,6 +245,13 @@ def wav_chunk_header(sample_rate=44100, bit_depth=16, channels=1):
     return wav_header_bytes
 
 
+def normalize_text(user_input, use_normalization):
+    if use_normalization:
+        return ChnNormedText(raw_text=user_input).normalize()
+    else:
+        return user_input
+
+
 def build_app():
     with gr.Blocks(theme=gr.themes.Base()) as app:
         gr.Markdown(HEADER_MD)
@@ -258,8 +267,24 @@ def build_app():
         with gr.Row():
             with gr.Column(scale=3):
                 text = gr.Textbox(
-                    label=i18n("Input Text"), placeholder=TEXTBOX_PLACEHOLDER, lines=15
+                    label=i18n("Input Text"), placeholder=TEXTBOX_PLACEHOLDER, lines=10
                 )
+                refined_text = gr.Textbox(
+                    label=i18n("Realtime Transform Text"),
+                    placeholder=i18n(
+                        "Normalization Result Preview (Currently Only Chinese)"
+                    ),
+                    lines=5,
+                    interactive=False,
+                )
+
+                with gr.Row():
+                    if_refine_text = gr.Checkbox(
+                        label=i18n("Text Normalization"),
+                        value=True,
+                        scale=0,
+                        min_width=150,
+                    )
 
                 with gr.Row():
                     with gr.Tab(label=i18n("Advanced Config")):
@@ -368,11 +393,16 @@ def build_app():
                             value="\U0001F3A7 " + i18n("Streaming Generate"),
                             variant="primary",
                         )
+
+        text.input(
+            fn=normalize_text, inputs=[text, if_refine_text], outputs=[refined_text]
+        )
+
         # # Submit
         generate.click(
             inference_wrapper,
             [
-                text,
+                refined_text,
                 enable_reference_audio,
                 reference_audio,
                 reference_text,
@@ -391,7 +421,7 @@ def build_app():
         generate_stream.click(
             inference_stream,
             [
-                text,
+                refined_text,
                 enable_reference_audio,
                 reference_audio,
                 reference_text,
@@ -413,10 +443,10 @@ def parse_args():
     parser.add_argument(
         "--llama-checkpoint-path",
         type=Path,
-        default="checkpoints/text2semantic-sft-medium-v1-4k.pth",
+        default="checkpoints/text2semantic-sft-large-v1.1-4k.pth",
     )
     parser.add_argument(
-        "--llama-config-name", type=str, default="dual_ar_2_codebook_medium"
+        "--llama-config-name", type=str, default="dual_ar_2_codebook_large"
     )
     parser.add_argument(
         "--decoder-checkpoint-path",