Yingzhi WANG

Hi @jqug, thank you for pointing this out, could you please finish the CI test so that we can finally merge this fix? (Please first pull the latest commits)

Hi @WillQuCD, first thanks for your interest in our benchmark paper, and also thank you for pointing this out. Yes, as you mentioned, the IEMOCAP results reported in this paper...

Hi @saharghannay, we never met this error before so I am not sure. However, I think you've done some modifications in your `train_with_wav2vec_new.yaml`, did it work with the origin `train_with_wav2vec.yaml`...

Hi @TParcollet , I think it's good for a system pure-CTC/greedy/without LM. Hybrid models from espnet got better CER: model | Test CER | Dev CER | LM -- |...

Yes exact. Fair enough, but their [branchformer](https://arxiv.org/pdf/2207.02971.pdf) is quite something according to the results.

Hi @anautsch thanks for the review, the fix is done. And yes that's why I want to reduce pandas, it is only used to generate csv for all the recipes.

Hi @TParcollet @anautsch @Adel-Moumen, Thank you all for the reviews and tests! The HF link is added, here's a brief summary of the PR: 1. add a CTC recipe 2....

Hi @olahsymbo100 thank you for your interest. We don't have a TTS fine-tuning tuto. But if you want to fine-tune a TTS model, you can load the model and fine-tune...

Hi @olahsymbo100, the `pretrainer` class does not have a fit method. Once the `pretrainer` loads the modules, you only need to launch the same training pipeline as in `train.py` with...

Hi @anautsch @mravanelli , I just bumped into this PR and I'll try to find some time to pick it up, since the dimensional approach is quite important in emotion...