Download Models for the HuggingFace_ASR Speech Recognition Channel

The HuggingFace_ASR speech recognition channel was added after v3.91. It supports using models from huggingface.co for speech recognition. The first time you use a model, it will be downloaded automatically. Downloads from https://huggingface.co or the domestic mirror https://hf-mirror.com may fail due to network restrictions. You can also download the files manually and place them in the corresponding location using the methods below.

Note: Do not rename the files after downloading. If your download directory already has a file with the same name, the system might automatically create a name like xxx(1). Please delete the old file and rename the new one to match the name shown on the download page.

Usable Models and Supported Languages

• nvidia/parakeet-ctc-1.1b: Supports recognizing audio/video with English pronunciation.

• reazon-research/japanese-wav2vec2-large-rs35kh: Supports recognizing audio/video with Japanese pronunciation.

• kotoba-tech/kotoba-whisper-v2.0: Supports recognizing audio/video with Japanese pronunciation.

• zh-plus/faster-whisper-large-v2-japanese-5k-steps: Supports recognizing audio/video with Japanese pronunciation.

• JhonVanced/whisper-large-v3-japanese-4k-steps-ct2: Supports recognizing audio/video with Japanese pronunciation.

• jonatasgrosman/wav2vec2-large-xlsr-53-japanese: Supports recognizing audio/video with Japanese pronunciation.

• suzii/vi-whisper-large-v3-turbo-v1: Supports recognizing audio/video with Vietnamese pronunciation.

• biodatlab/whisper-th-medium: Supports recognizing audio/video with Thai pronunciation.

• biodatlab/whisper-th-large-v3: Supports recognizing audio/video with Thai pronunciation.

Manual Download

• Manually download nvidia/parakeet-ctc-1.1b:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--nvidia--parakeet-ctc-1.1b and navigate into it.
  2. Open the model download page: https://huggingface.co/nvidia/parakeet-ctc-1.1b/tree/main
  3. Download all files from that page and copy them into the folder you created above.

• Manually download reazon-research/japanese-wav2vec2-large-rs35kh:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--reazon-research--japanese-wav2vec2-large-rs35kh and navigate into it.
  2. Open the model download page: https://huggingface.co/reazon-research/japanese-wav2vec2-large-rs35kh/tree/main
  3. Download all files from that page and copy them into the folder you created above.

• Manually download kotoba-tech/kotoba-whisper-v2.0:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--kotoba-tech--kotoba-whisper-v2.0 and navigate into it.
  2. Open the model download page: https://huggingface.co/kotoba-tech/kotoba-whisper-v2.0/tree/main
  3. Download all files from that page and copy them into the folder you created above.

• Manually download zh-plus/faster-whisper-large-v2-japanese-5k-steps:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--zh-plus--faster-whisper-large-v2-japanese-5k-steps and navigate into it.
  2. Open the model download page: https://huggingface.co/zh-plus/faster-whisper-large-v2-japanese-5k-steps/tree/main
  3. Download all files from that page and copy them into the folder you created above.

• Manually download JhonVanced/whisper-large-v3-japanese-4k-steps-ct2:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--JhonVanced--whisper-large-v3-japanese-4k-steps-ct2 and navigate into it.
  2. Open the model download page: https://huggingface.co/JhonVanced/whisper-large-v3-japanese-4k-steps-ct2/tree/main
  3. Download all files from that page and copy them into the folder you created above.

• Manually download jonatasgrosman/wav2vec2-large-xlsr-53-japanese:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--jonatasgrosman--wav2vec2-large-xlsr-53-japanese and navigate into it.
  2. Open the model download page: https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-japanese/tree/main
  3. Download all files from that page and copy them into the folder you created above.

• Manually download suzii/vi-whisper-large-v3-turbo-v1:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--suzii--vi-whisper-large-v3-turbo-v1 and navigate into it.
  2. Open the model download page: https://huggingface.co/suzii/vi-whisper-large-v3-turbo-v1/tree/main
  3. Download all files from that page and copy them into the folder you created above.

• Manually download biodatlab/whisper-th-medium:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--biodatlab--whisper-th-medium and navigate into it.
  2. Open the model download page: https://huggingface.co/biodatlab/whisper-th-medium/tree/main
  3. Download all files from that page and copy them into the folder you created above.

• Manually download biodatlab/whisper-th-large-v3:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--biodatlab--whisper-th-large-v3 and navigate into it.
  2. Open the model download page: https://huggingface.co/biodatlab/whisper-th-large-v3/tree/main
  3. Download all files from that page and copy them into the folder you created above.

---

Download Models for the openai-whisper Channel

Models for this channel are single .pt files. After downloading, place them in the models folder at the same level as sp.py(sp.exe).

• tiny.en.pt : https://openaipublic.azureedge.net/main/whisper/models/d3dd57d32accea0b295c96e26691aa14d8822fac7d9d27d5dc00b4ca2826dd03/tiny.en.pt

• tiny.pt: https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt

• base.en.pt: https://openaipublic.azureedge.net/main/whisper/models/25a8566e1d0c1e2231d1c762132cd20e0f96a85d16145c3a00adf5d1ac670ead/base.en.pt

• base.pt: https://openaipublic.azureedge.net/main/whisper/models/ed3a0b6b1c0edf879ad9b11b1af5a0e6ab5db9205f891f668f8b0e6c6326e34e/base.pt

• small.en.pt: https://openaipublic.azureedge.net/main/whisper/models/f953ad0fd29cacd07d5a9eda5624af0f6bcf2258be67c92b79389873d91e0872/small.en.pt

• small.pt: https://openaipublic.azureedge.net/main/whisper/models/9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794/small.pt

• medium.en.pt: https://openaipublic.azureedge.net/main/whisper/models/d7440d1dc186f76616474e0ff0b3b6b879abc9d1a4926b7adfa41db2d497ab4f/medium.en.pt

• medium.pt: https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt

• large-v1.pt: https://openaipublic.azureedge.net/main/whisper/models/e4b87e7e0bf463eb8e6956e646f1e277e901512310def2c24bf0e11bd3c28e9a/large-v1.pt

• large-v2.pt: https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt

• large-v3.pt: https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt

• large-v3-turbo.pt: https://openaipublic.azureedge.net/main/whisper/models/aff26ae408abcba5fbf8813c21e62b0941638c5f6eebfb145be0c9839262a19a/large-v3-turbo.pt

---

Download Models for the faster-whisper Channel

By default, models are automatically downloaded from https://huggingface.co. This site is blocked in China, making access impossible without a VPN. Within China, the mirror site https://hf-mirror.com will be used automatically, but it may be unstable and downloads can fail. If they fail, please download manually using the methods below.

• tiny model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(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/.txt files from that page and copy them into the folder you created above.

• tiny.en model:

  1. Create a folder: Inside the models folder at the same level 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/.txt files from that page and copy them into the folder you created above.

• base model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-base.
  2. Open the model download page: https://huggingface.co/Systran/faster-whisper-base/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• base.en model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-base.en.
  2. Open the model download page: https://huggingface.co/Systran/faster-whisper-base.en/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• small model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-small.
  2. Open the model download page: https://huggingface.co/Systran/faster-whisper-small/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• small.en model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-small.en.
  2. Open the model download page: https://huggingface.co/Systran/faster-whisper-small.en/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• medium model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-medium.
  2. Open the model download page: https://huggingface.co/Systran/faster-whisper-medium/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• medium.en model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-medium.en.
  2. Open the model download page: https://huggingface.co/Systran/faster-whisper-medium.en/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• large-v3-turbo model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--mobiuslabsgmbh--faster-whisper-large-v3-turbo.
  2. Open the model download page: https://huggingface.co/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• large-v1 model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-large-v1.
  2. Open the model download page: https://huggingface.co/Systran/faster-whisper-large-v1/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• large-v2 model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-large-v2.
  2. Open the model download page: https://huggingface.co/Systran/faster-whisper-large-v2/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• large-v3 model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--Systran--faster-whisper-large-v3.
  2. Open the model download page: https://huggingface.co/Systran/faster-whisper-large-v3/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• distil-small.en model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--Systran--faster-distil-whisper-small.en.
  2. Open the model download page: https://huggingface.co/Systran/faster-distil-whisper-small.en/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• distil-medium.en model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--Systran--faster-distil-whisper-medium.en.
  2. Open the model download page: https://huggingface.co/Systran/faster-distil-whisper-medium.en/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• distil-large-v2 model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--Systran--faster-distil-whisper-large-v2.
  2. Open the model download page: https://huggingface.co/Systran/faster-distil-whisper-large-v2/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• distil-large-v3 model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--Systran--faster-distil-whisper-large-v3.
  2. Open the model download page: https://huggingface.co/Systran/faster-distil-whisper-large-v3/tree/main
  3. Download all .json/.bin/.txt files from that page and copy them into the folder you created above.

• distil-large-v3.5 model:

  1. Create a folder: Inside the models folder at the same level as sp.exe(sp.py), create a folder named models--distil-whisper--distil-large-v3.5-ct2.
  2. Open the model download page: 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 into the folder you created above.

---

Download the M2M100 Translation Model

Download URL: https://modelscope.cn/models/himyworld/videotrans/resolve/master/m2m100_12b_model.zip

After extraction, you will get a folder named m2m100_12b. Copy this folder into the models folder located in the same directory as sp.py(sp.exe).

---

Download Models for the VITS Dubbing Channel and Piper-TTS Dubbing Channel

• VITS-TTS Channel: 175 Chinese voice styles, 109 English voice styles. Does not support dubbing in other languages.

  Model Download URL: https://modelscope.cn/models/himyworld/videotrans/resolve/master/vits-tts.zip

  After downloading and extracting, you will see a folder named vits. Copy this folder into the models folder located in the same directory as sp.exe (or sp.py for source code deployment).

• Piper-TTS Channel: Supports dubbing in 20 languages. However, to reduce model size and avoid downloading unnecessary models, by default it only supports one Chinese voice style and 10 English voice styles. Model Download URL: https://modelscope.cn/models/himyworld/videotrans/resolve/master/piper-tts.zip

  After downloading and extracting, you will see a folder named piper. Copy this folder into the models folder located in the same directory as sp.exe (or sp.py for source code deployment).