| .. |
|
llama
|
9e2f5e6b3a
Avoid cuda-dependent code for CPU-only inference (#499)
|
1 rok temu |
|
sensevoice
|
8702c61100
From whisper to sensevoice (#482)
|
1 rok temu |
|
vqgan
|
e029f38485
Fix import path in inference.py (#487)
|
1 rok temu |
|
api.py
|
8702c61100
From whisper to sensevoice (#482)
|
1 rok temu |
|
auto_rerank.py
|
979b0e5523
Optimize dp etc. (#407)
|
1 rok temu |
|
download_models.py
|
eb35b0b1c6
Fix around asr bugs (#401)
|
1 rok temu |
|
extract_model.py
|
c25c946695
Update vqgan toolchain
|
2 lat temu |
|
file.py
|
8702c61100
From whisper to sensevoice (#482)
|
1 rok temu |
|
gen_ref.py
|
1e83d31959
API support: ref audio (#241)
|
1 rok temu |
|
merge_asr_files.py
|
8702c61100
From whisper to sensevoice (#482)
|
1 rok temu |
|
post_api.py
|
5a842d1d40
more stable streaming audio play and save (#477)
|
1 rok temu |
|
smart_pad.py
|
8702c61100
From whisper to sensevoice (#482)
|
1 rok temu |
|
webui.py
|
cc7afe8d7b
Support inference on mps device natively (#461)
|
1 rok temu |
|
whisper_asr.py
|
8702c61100
From whisper to sensevoice (#482)
|
1 rok temu |
Sergey Aleynikov
9e2f5e6b3a
Avoid cuda-dependent code for CPU-only inference (#499)