Automatic Speech Recognition
Transformers
PyTorch
Hindi
wav2vec2
Generated from Trainer
robust-speech-event
hf-asr-leaderboard
# Load model directly
from transformers import AutoProcessor, AutoModelForCTC
processor = AutoProcessor.from_pretrained("ravirajoshi/wav2vec2-large-xls-r-300m-hindi-lm-boosted")
model = AutoModelForCTC.from_pretrained("ravirajoshi/wav2vec2-large-xls-r-300m-hindi-lm-boosted", device_map="auto")Quick Links
wav2vec2-large-xls-r-300m-hindi
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: 0.7049
- Wer: 0.3200
- Downloads last month
- 7
Model tree for ravirajoshi/wav2vec2-large-xls-r-300m-hindi-lm-boosted
Base model
facebook/wav2vec2-xls-r-300m
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ravirajoshi/wav2vec2-large-xls-r-300m-hindi-lm-boosted")