Automatic Speech Recognition
Transformers
Safetensors
seamless_m4t_v2
feature-extraction
audio-to-audio
text-to-speech
seamless_communication
Instructions to use facebook/seamless-m4t-v2-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/seamless-m4t-v2-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="facebook/seamless-m4t-v2-large")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("facebook/seamless-m4t-v2-large") model = AutoModel.from_pretrained("facebook/seamless-m4t-v2-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
The model can't be downloaded
#30
by JadwalAlmaa - opened
I am using the code provided by hugginface https://huggingface.co/docs/transformers/en/model_doc/seamless_m4t_v2
but there is an error accrue
ImportError: cannot import name 'SeamlessM4Tv2Model' from 'transformers' (/usr/local/lib/python3.10/dist-packages/transformers/init.py)
Try to use an older version of python, it works fine on 3.9. Hope this helps!