This article introduces the method of manually downloading models from the huggingface website after a download failure in the faster-whisper[Local] speech recognition channel, as well as download addresses for other related models used in the software.

Make sure you have upgraded to version v3.91

When using the faster-whisper[Local] speech recognition channel, you need to download the model from the overseas website https://huggingface.co or from the domestic mirror https://hf-mirror.com. The former requires a stable and reliable proxy tool, otherwise it is prone to failure. The latter mirror site itself seems to have unstable network, often leading to download timeouts and failures.

Manually Download Models for the faster-whisper (Local) Channel

Choose the model according to your needs. The best model is large-v3. Without CUDA acceleration, ensure RAM is at least 16GB. With CUDA acceleration, ensure VRAM is over 10GB.

• Download the tiny model:

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-tiny.
  2. Open the model download address: https://huggingface.co/Systran/faster-whisper-tiny/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the tiny.en model (English speech recognition only):

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-tiny.en.
  2. Open the model download address: https://huggingface.co/Systran/faster-whisper-tiny.en/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the base model:

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-base.
  2. Open the model download address: https://huggingface.co/Systran/faster-whisper-base/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the base.en model (English speech recognition only):

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-base.en.
  2. Open the model download address: https://huggingface.co/Systran/faster-whisper-base.en/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the small model:

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-small.
  2. Open the model download address: https://huggingface.co/Systran/faster-whisper-small/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the small.en model (English speech recognition only):

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-small.en.
  2. Open the model download address: https://huggingface.co/Systran/faster-whisper-small.en/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the medium model:

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-medium.
  2. Open the model download address: https://huggingface.co/Systran/faster-whisper-medium/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the medium.en model (English speech recognition only):

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-medium.en.
  2. Open the model download address: https://huggingface.co/Systran/faster-whisper-medium.en/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the large-v3-turbo model:

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--mobiuslabsgmbh--faster-whisper-large-v3-turbo.
  2. Open the model download address: https://huggingface.co/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the large-v1 model:

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-large-v1.
  2. Open the model download address: https://huggingface.co/Systran/faster-whisper-large-v1/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the large-v2 model:

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-large-v2.
  2. Open the model download address: https://huggingface.co/Systran/faster-whisper-large-v2/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the large-v3 model:

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-large-v3.
  2. Open the model download address: https://huggingface.co/Systran/faster-whisper-large-v3/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

---

The following distilled models can only be used for recognizing and transcribing English speech in audio/video.

• Download the distil-large-v3 model:

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-distil-whisper-large-v3.
  2. Open the model download address: https://huggingface.co/Systran/faster-distil-whisper-large-v3/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the distil-large-v3.5 model:

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--distil-whisper--distil-large-v3.5-ct2.
  2. Open the model download address: https://huggingface.co/distil-whisper/distil-large-v3.5-ct2/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the distil-small.en model:

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-distil-whisper-small.en.
  2. Open the model download address: https://huggingface.co/Systran/faster-distil-whisper-small.en/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the distil-medium.en model:

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-distil-whisper-medium.en.
  2. Open the model download address: https://huggingface.co/Systran/faster-distil-whisper-medium.en/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

• Download the distil-large-v2 model:

  1. Create a folder: Inside the models folder in the same directory as sp.exe(sp.py), create a folder named models--Systran--faster-distil-whisper-large-v2.
  2. Open the model download address: https://huggingface.co/Systran/faster-distil-whisper-large-v2/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them to the folder you just created. Overwrite if files already exist.

Domestic Mirror Address for faster-whisper Models

https://modelscope.cn/models/himyworld/fasterwhisper/files

Noise Reduction Model, Voice/Sound Separation Model, m2m100 Model, Real-time Speech Recognition Model, VITS Model, Built-in Speaker Diarization Model

https://modelscope.cn/models/himyworld/videotrans/files