pyVideoTrans

Appearance

All Models and Download Links for This Software ​

To keep the software package lightweight, no AI models are pre-installed. Models will be downloaded automatically the first time you use them, mainly from the global repository huggingface.co, mirror sites like hf-mirror.com, and Alibaba ModelScope (modelscope.cn).

This page lists the download links for all supported models and their required local storage locations. If automatic downloads keep failing, you can delete any partially downloaded files and download them manually.

Notes on Model Downloads:

  • Models are generally large in size. Accessing overseas repositories directly may require a stable network/proxy connection. When unavailable, the software will automatically attempt to switch to mirror sites.
  • Even with a proxy, downloads might still fail if the connection is unstable.
  • Mirror sites often enforce rate limits, and their download speeds can fluctuate.
  • Due to these reasons, download failures are quite common, and many unexpected errors are indirectly caused by incomplete model downloads.

"Software Directory" refers to the folder where sp.exe or sp.py is located.

Important Download Tips

A model usually consists of multiple files, and different models may share identical file names (for example, many include model.safetensors). If a file with the same name already exists in your browser's download folder, your browser may automatically rename it (e.g., model.safetensors becomes model(2).safetensors). You must rename it back to its original name before moving it to the specified folder; otherwise, the software will not recognize it.

On huggingface.co, click the download icon next to each file to download it:

Speech Recognition (ASR) Models ​

Qwen-ASR (Built-in) ​

0.6B Model:

1.7B Model:

CN-Dialect(Chinese Dialect)：

Firered Chinese (Built-in) ​

Dolphin (Built-in) ​

Omnilingual Asian Languages (Built-in) ​

parakeet Japanese (Built-in) ​

Moss-Diarize (Built-in) ​

faster-whisper (Built-in) ​

Model NameLocal Storage LocationDownload Link
tinySoftware Directory/models/models--Systran--faster-whisper-tinyhttps://huggingface.co/Systran/faster-whisper-tiny/tree/main
baseSoftware Directory/models/models--Systran--faster-whisper-basehttps://huggingface.co/Systran/faster-whisper-base/tree/main
smallSoftware Directory/models/models--Systran--faster-whisper-smallhttps://huggingface.co/Systran/faster-whisper-small/tree/main
mediumSoftware Directory/models/models--Systran--faster-whisper-mediumhttps://huggingface.co/Systran/faster-whisper-medium/tree/main
large-v1Software Directory/models/models--Systran--faster-whisper-large-v1https://huggingface.co/Systran/faster-whisper-large-v1/tree/main
large-v2Software Directory/models/models--Systran--faster-whisper-large-v2https://huggingface.co/Systran/faster-whisper-large-v2/tree/main
large-v3Software Directory/models/models--Systran--faster-whisper-large-v3https://huggingface.co/Systran/faster-whisper-large-v3/tree/main
large-v3-turboSoftware Directory/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbohttps://huggingface.co/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main
---------
tiny.enSoftware Directory/models/models--Systran--faster-whisper-tiny.enhttps://huggingface.co/Systran/faster-whisper-tiny.en/tree/main
base.enSoftware Directory/models/models--Systran--faster-whisper-base.enhttps://huggingface.co/Systran/faster-whisper-base.en/tree/main
small.enSoftware Directory/models/models--Systran--faster-whisper-small.enhttps://huggingface.co/Systran/faster-whisper-small.en/tree/main
medium.enSoftware Directory/models/models--Systran--faster-whisper-medium.enhttps://huggingface.co/Systran/faster-whisper-medium.en/tree/main
---------
distil-large-v2Software Directory/models/models--Systran--faster-distil-whisper-large-v2https://huggingface.co/Systran/faster-distil-whisper-large-v2/tree/main
distil-large-v3Software Directory/models/models--Systran--faster-distil-whisper-large-v3https://huggingface.co/Systran/faster-distil-whisper-large-v3/tree/main
distil-large-v3.5Software Directory/models/models--distil-whisper--distil-large-v3.5-ct2https://huggingface.co/distil-whisper/distil-large-v3.5-ct2/tree/main
distil-small.enSoftware Directory/models/models--Systran--faster-distil-whisper-small.enhttps://huggingface.co/Systran/faster-distil-whisper-small.en/tree/main
distil-medium.enSoftware Directory/models/models--Systran--faster-distil-whisper-medium.enhttps://huggingface.co/Systran/faster-distil-whisper-medium.en/tree/main

openai-whisper (Built-in) ​

Place downloaded .pt model files directly into the Software Directory/models folder.

HuggingFace_ASR (Built-in) ​

whisper.cpp ​

Single-file models: Place the downloaded .bin file into the Software Directory/models folder.

Subtitle Translation Models ​

Hy-MT2-1.8B (Built-in) ​

M2M100 (Built-in) ​

Dubbing & Text-to-Speech (TTS) Models ​

Piper (Built-in) ​

VITS (Built-in) ​

ZipVoice (Built-in) ​

OmniVoice (Built-in) ​

MOSS-TTS-Nano (Built-in) ​

ChatterBox (Built-in) ​

Supertonic (Built-in) ​

Higgs-audio-v3 (Built-in) ​

Qwen3-TTS (Built-in) ​

Confucius-TTS (Built-in) ​

F5-TTS (Built-in) ​

Storage location: Software Directory/models/models--SWivid--F5-TTS/F5TTS_v1_Base

Storage location: Software Directory/models/models--Jmica--F5TTS/JA_21999120

Storage location: Software Directory/models/models--RASPIAUDIO--F5-French-MixedSpeakers-reduced

Storage location: Software Directory/models/models--hvoss-techfak--F5-TTS-German

Storage location: Software Directory/models/models--hotstone228--F5-TTS-Russian

Storage location: Software Directory/models/models--alien79--F5-TTS-italian

Storage location: Software Directory/models/models--jpgallegoar--F5-Spanish

Storage location: Software Directory/models/models--SPRINGLab/F5-Hindi-24KHz

Storage location: Software Directory/models/models--silma-ai--silma-tts

Storage location: Software Directory/models/models--multilingual-tts--F5-TTS-OpenBible-Turkish

Storage location: Software Directory/models/models--multilingual-tts--F5-TTS-OpenBible-Vietnamese

Speaker Diarization Models ​

Built-in Models: ​

On this page, download the following 3 files: 3dspeaker_speech_eres2net_large_sv_zh-cn_3dspeaker_16k.onnx, nemo_en_titanet_small.onnx, and seg_model.onnx.

  • Storage location: Place the 3 downloaded files into Software Directory/models/onnx/

pyannote ​

Ali camp++: ​

Vocal Separation, Noise Reduction, and Punctuation Restoration Models ​

Real-time Speech Recognition Models ​