The content on this page is sourced from my open-source project release page. For the latest information, please visit GitHub: https://github.com/jianchang512/stt/releases/0.0
Faster-Whisper Model Downloads – Suitable for the stt project and the faster-whisper mode in "pyvideotrans video translation and dubbing" project. For OpenAI-Whisper models, scroll down.
small 415MBsmall Baidu Netdisksmall.en 415MB
large-v1 Baidu Netdisklarge-v1 HuggingFace
large-v2 HuggingFacelarge-v2 Baidu Netdisk
large-v3 HuggingFacelarge-v3 Baidu Netdisk
distil-whisper-medium.en 671MBdistil-medium Baidu Netdisk
distil-whisper-large-v2 1.27Gdistil-large-v2 Baidu Netdisk
distil-whisper-large-v3 1.3Gdistil-whisper-large-v3 Baidu Netdisk
After downloading, extract the archive and copy the "models--Systran--faster-xx" folder inside to the models directory. After extraction and copying, the folder list under the models directory should look like this:
Archive contents:
Correct folder list under the models directory after placement:
OpenAI-Whisper Model Downloads – Only for use with the openai-whisper mode in "pyvideotrans video translation and dubbing software"
After downloading, place the .pt file into the models folder under the software directory.
FunASR Chinese Model Downloads
Baidu Netdisk download (includes speech recognition, punctuation restoration, and noise reduction models): https://pan.baidu.com/s/1v5wagiid6-K7GX9Pif4reA?pwd=y2ef
HuggingFace (external download link): https://huggingface.co/spaces/mortimerme/s4/resolve/main/FunASR-Chinese-models.7z?download=true
After downloading and extracting, you will see three folders:
iic
,damo
, and.__temp
. Copy them to themodels/hub
folder in the video translation software, overwriting if necessary.
cuBLASxx.dll and cuDNN Downloads
If you encounter "cublasxxx.dll not found" or the software crashes after enabling CUDA acceleration, download the corresponding file and copy the .dll files inside to either C:/Windows/System32
or the software's root directory (where the .exe is located).
Open a command prompt by typing cmd
in any folder's address bar, then run the command nvcc -V
to check your current CUDA version.
For CUDA 11.x, click here to download: https://github.com/jianchang512/stt/releases/download/0.0/cuBLAS.and.cuDNN_CUDA11_win_v4.7z
For CUDA 12.x, click here to download: https://github.com/jianchang512/stt/releases/download/0.0/cuBLAS.and.cuDNN_CUDA12_win_v1.7z
UVR5 Model Download
After downloading and extracting, you will get a uvr5_weights
folder. Copy this folder to the root directory of the video translation and dubbing software.
ffmpeg.exe Download
If you are on Windows and receive a "ffmpeg command not found" error, you can download the following two files and place them in the software's root directory or in the ffmpeg folder under the root directory.
https://github.com/jianchang512/stt/releases/download/0.0/ffmpeg.exe
https://github.com/jianchang512/stt/releases/download/0.0/ffprobe.exe