Automatic Speech Recognition
Transformers
PyTorch
Marathi
wav2vec2
Generated from Trainer
hf-asr-leaderboard
robust-speech-event
Instructions to use ravirajoshi/wav2vec2-large-xls-r-300m-marathi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ravirajoshi/wav2vec2-large-xls-r-300m-marathi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ravirajoshi/wav2vec2-large-xls-r-300m-marathi")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("ravirajoshi/wav2vec2-large-xls-r-300m-marathi") model = AutoModelForCTC.from_pretrained("ravirajoshi/wav2vec2-large-xls-r-300m-marathi") - Notebooks
- Google Colab
- Kaggle
wav2vec2-large-xls-r-300m-marathi
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5656
- Wer: 0.2156
- Downloads last month
- 16