Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Marathi
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use anuragshas/whisper-small-mr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anuragshas/whisper-small-mr with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="anuragshas/whisper-small-mr")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("anuragshas/whisper-small-mr") model = AutoModelForSpeechSeq2Seq.from_pretrained("anuragshas/whisper-small-mr") - Notebooks
- Google Colab
- Kaggle
Whisper Small Marathi
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 mr dataset. It achieves the following results on the evaluation set:
- Loss: 0.4888
- Wer: 19.71
- Downloads last month
- 10
Space using anuragshas/whisper-small-mr 1
Evaluation results
- Wer on mozilla-foundation/common_voice_11_0 mrtest set self-reported19.710