This article describes how to manually download models from the Hugging Face website if the faster-whisper [local] speech recognition channel fails to download.

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 external website https://huggingface.co or from a domestic mirror https://hf-mirror.com. The former requires a VPN/proxy with a stable and reliable connection, otherwise it can easily fail. The latter mirror site itself seems to have unstable network connections, often leading to download timeouts.

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

Choose the model you want to use. The best model is large-v3. When not using CUDA acceleration, ensure at least 16GB of RAM; with CUDA acceleration, ensure at least 10GB of VRAM.

• Download the tiny model:

  1. Create a folder: In the models folder located in the same directory as sp.exe (or sp.py), create a folder named models--Systran--faster-whisper-tiny.
  2. Open the model download page: https://huggingface.co/Systran/faster-whisper-tiny/tree/main
  3. Download all .json, .bin, and .txt files from that page and copy them into the folder you created. If files already exist, you can overwrite them directly.

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

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

• Download the base model:

  1. Create a folder named models--Systran--faster-whisper-base inside the models folder.
  2. Open the download page: https://huggingface.co/Systran/faster-whisper-base/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

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

  1. Create a folder named models--Systran--faster-whisper-base.en inside the models folder.
  2. Open the download page: https://huggingface.co/Systran/faster-whisper-base.en/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

• Download the small model:

  1. Create a folder named models--Systran--faster-whisper-small inside the models folder.
  2. Open the download page: https://huggingface.co/Systran/faster-whisper-small/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

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

  1. Create a folder named models--Systran--faster-whisper-small.en inside the models folder.
  2. Open the download page: https://huggingface.co/Systran/faster-whisper-small.en/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

• Download the medium model:

  1. Create a folder named models--Systran--faster-whisper-medium inside the models folder.
  2. Open the download page: https://huggingface.co/Systran/faster-whisper-medium/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

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

  1. Create a folder named models--Systran--faster-whisper-medium.en inside the models folder.
  2. Open the download page: https://huggingface.co/Systran/faster-whisper-medium.en/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

• Download the large-v3-turbo model:

  1. Create a folder named models--mobiuslabsgmbh--faster-whisper-large-v3-turbo inside the models folder.
  2. Open the download page: https://huggingface.co/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

• Download the large-v1 model:

  1. Create a folder named models--Systran--faster-whisper-large-v1 inside the models folder.
  2. Open the download page: https://huggingface.co/Systran/faster-whisper-large-v1/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

• Download the large-v2 model:

  1. Create a folder named models--Systran--faster-whisper-large-v2 inside the models folder.
  2. Open the download page: https://huggingface.co/Systran/faster-whisper-large-v2/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

• Download the large-v3 model:

  1. Create a folder named models--Systran--faster-whisper-large-v3 inside the models folder.
  2. Open the download page: https://huggingface.co/Systran/faster-whisper-large-v3/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

---

The following distilled models are only suitable for transcribing English audio/video content.

• Download the distil-large-v3 model:

  1. Create a folder named models--Systran--faster-distil-whisper-large-v3 inside the models folder.
  2. Open the download page: https://huggingface.co/Systran/faster-distil-whisper-large-v3/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

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

  1. Create a folder named models--distil-whisper--distil-large-v3.5-ct2 inside the models folder.
  2. Open the download page: https://huggingface.co/distil-whisper/distil-large-v3.5-ct2/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

• Download the distil-small.en model:

  1. Create a folder named models--Systran--faster-distil-whisper-small.en inside the models folder.
  2. Open the download page: https://huggingface.co/Systran/faster-distil-whisper-small.en/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

• Download the distil-medium.en model:

  1. Create a folder named models--Systran--faster-distil-whisper-medium.en inside the models folder.
  2. Open the download page: https://huggingface.co/Systran/faster-distil-whisper-medium.en/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.

• Download the distil-large-v2 model:

  1. Create a folder named models--Systran--faster-distil-whisper-large-v2 inside the models folder.
  2. Open the download page: https://huggingface.co/Systran/faster-distil-whisper-large-v2/tree/main
  3. Download all .json, .bin, and .txt files and copy them into the folder. Overwrite if needed.