Wav2Vec2-Large-XLSR-53-Telugu
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Telugu using the ASR IIIT-H dataset. When using this model, make sure that your speech input is sampled at 16kHz.
Test Result: 41.90%
Training
70% of the O part of ASR IIIT-H Telugu dataset was used for training.
Unable to determine this model's library. Check the
docs
.
Evaluation results
- Test WERself-reported41.900