Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
infinitejoy
/
wav2vec2-large-xls-r-300m-assamese
like
1
Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
mozilla-foundation/common_voice_7_0
Assamese
wav2vec2
audio
speech
xlsr-fine-tuning
robust-speech-event
hf-asr-leaderboard
Eval Results
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
1
Train
Deploy
Use this model
main
wav2vec2-large-xls-r-300m-assamese
/
mozilla-foundation_common_voice_7_0_as_test_eval_results.txt
infinitejoy
eval results
76bd87a
almost 3 years ago
raw
Copy download link
history
blame
contribute
delete
Safe
48 Bytes
WER: 0.7954545454545454
CER: 0.32341269841269843