Automatic Speech Recognition
Transformers
Safetensors
Nepali
whisper
nepali
fine-tuned
audio
asr
Eval Results (legacy)
Instructions to use devrahulbanjara/whisper-small-nepali with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use devrahulbanjara/whisper-small-nepali with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="devrahulbanjara/whisper-small-nepali")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("devrahulbanjara/whisper-small-nepali") model = AutoModelForMultimodalLM.from_pretrained("devrahulbanjara/whisper-small-nepali") - Notebooks
- Google Colab
- Kaggle
| { | |
| "add_prefix_space": false, | |
| "backend": "tokenizers", | |
| "bos_token": "<|endoftext|>", | |
| "eos_token": "<|endoftext|>", | |
| "is_local": true, | |
| "language": null, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "predict_timestamps": false, | |
| "processor_class": "WhisperProcessor", | |
| "task": null, | |
| "tokenizer_class": "WhisperTokenizer", | |
| "unk_token": "<|endoftext|>" | |
| } | |