jonatasgrosman / wav2vec2-sprint

jonatasgrosman/wav2vec2-sprint Issues

Generate the N-best (top few) hypotheses
Updated a year ago
How to get the phoneme?
Updated a year ago2
Export model to ONNX
Updated a year ago2
YAML Metadata Error: "language[0]" must only contain lowercase characters for zh-CN
Updated 2 years ago
wav2vec2-xls-r-1b_cv8_it
Updated 2 years ago
Predictions are always pad_token, logits are always the same distribution for different time_step and speech utterances.
Updated 2 years ago2
Wav2Vec2-XLSR-German-53
Updated 2 years ago1
I can't run to train model
Updated 3 years ago2
Congratulations with great model!
Closed 3 years ago2
how much does the model gain in performance doing audio augmentations ?
Updated 3 years ago1
settings
Updated 3 years ago4
Finetune model for Japanese language with LaboroTVSpeech corpus
Updated 3 years ago1