Craya
Craya
Dear Team, I want to compare the ASR results we have reached based on wav2vec2 & whisper architectures, with your SummaryMixing one. We are performing a custom ASR training, our...
### Describe the bug Since speechbrain==1.0.3, I face an error when launching recipe CommonVoice/ASR/transformer/: `AttributeError: 'WhisperTokenizerFast' object has no attribute 'normalize'` ### Expected behaviour Recipe works fine ;-) ### To...
### Describe the bug I have a fine‑tuned wav2vec 2.0 model paired with a KenLM language model that delivers good performance. To make better use of the GPU I switched...