Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
mozilla-foundation/common_voice_8_0
Generated from Trainer
rm-vallader
robust-speech-event
model_for_talk
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use DrishtiSharma/wav2vec2-xls-r-300m-rm-vallader-d1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DrishtiSharma/wav2vec2-xls-r-300m-rm-vallader-d1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="DrishtiSharma/wav2vec2-xls-r-300m-rm-vallader-d1")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("DrishtiSharma/wav2vec2-xls-r-300m-rm-vallader-d1") model = AutoModelForCTC.from_pretrained("DrishtiSharma/wav2vec2-xls-r-300m-rm-vallader-d1") - Notebooks
- Google Colab
- Kaggle
File size: 225 Bytes
c32f5d8 | 1 2 3 4 5 6 7 8 9 | {
"epoch": 100.0,
"eval_loss": 0.2753646671772003,
"eval_runtime": 19.8089,
"eval_samples": 427,
"eval_samples_per_second": 21.556,
"eval_steps_per_second": 1.363,
"eval_wer": 0.28305984555984554
} |