Instructions to use Be-win/whisper-medium-malayalam with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Be-win/whisper-medium-malayalam with PEFT:
from peft import PeftModel from transformers import AutoModelForSpeechSeq2Seq base_model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-medium") model = PeftModel.from_pretrained(base_model, "Be-win/whisper-medium-malayalam") - Transformers
How to use Be-win/whisper-medium-malayalam with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Be-win/whisper-medium-malayalam", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from Be-win/whisper-medium-malayalam: direct link, hf CLI and curl.
- Browser
- Download file 3.93 MB
-
https://huggingface.co/Be-win/whisper-medium-malayalam/resolve/main/tokenizer.json
- Command line
-
hf download hf://Be-win/whisper-medium-malayalam/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/Be-win/whisper-medium-malayalam/resolve/main/tokenizer.json
3.93 MB
File too large to display, you can check the raw version instead.