louislau

Seems not work on speechocean dataset

1

Hi, @felixkreuk , first thank you for open-sourced such good repo on unsupervised phoneme segmentation. Recently, I conduct several experiments on SpeechOcean 762 dataset, which is a standard speech scoring...

Hi, for seq2seq model, I found the prefix-tuning method in peft currently only supports the seq2seq language model. This means it requires `input_ids` field to be the input to the...

Predictions are always pad_token, logits are always the same distribution for different time_step and speech utterances.

2

Hi, thanks for your wav2vec2 fine-tuning scripts first. Recently, I used this script (run_common_voice.py) to fine-tune the newest **Hubert model** for ASR on Chinese language (zh-CN). Hubert basically has the...