Instructions to use facebook/mms-1b-all with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/mms-1b-all with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="facebook/mms-1b-all")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("facebook/mms-1b-all") model = AutoModelForCTC.from_pretrained("facebook/mms-1b-all") - Notebooks
- Google Colab
- Kaggle
Target language UNKNOWN
#14
by airsheysr - opened
The inference API performs poorly on transcribing because it does not know the language being spoken. If you would allow the target language to be one of the post requests data, I think the model can have better transcription results by effectively using the appropriate language adapter. Please do consider this.