MMS ASR – Custom Fine-tuned Model

This model is a fine-tuned version of Meta AI's Massively Multilingual Speech (MMS) model for automatic speech recognition (ASR).

Base model

  • Meta AI – MMS (Wav2Vec2ForCTC)

License

This model is released under the Creative Commons Attribution–NonCommercial 4.0 (CC BY-NC 4.0) license.

You may use, modify, and share this model for non-commercial purposes only. Commercial use is not permitted.

Attribution

Please cite:

  • Meta AI, Massively Multilingual Speech (MMS)

Usage

from transformers import AutoProcessor, Wav2Vec2ForCTC

processor = AutoProcessor.from_pretrained("sb-x/mms-1b-bbl")
model = Wav2Vec2ForCTC.from_pretrained("sb-x/mms-1b-bbl")
Downloads last month
10
Safetensors
Model size
1.0B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Space using sb-x/mms-1b-bbl 1