GeeYang_ML

Unable to reproduce results from the paper

1

Hi. Can the exact code from `run_eval.py` be used to reproduce the results from Table 16 ? I tried to benchmark distill-whisper-v2 on `distil-whisper/common_voice_13_0` dataset and found the WER is...

Discrepancy on WER benchmark result in Tedlium dataset

1

Hi. I am unable to reproduce the benchmark results in the paper for test split in `distil-whisper/tedlium` using model `distil-whisper/distil-large-v2` when using `run_eval.py`. However, I am able to achieve reasonable...

Authentication method stopped working

2

I am unable to obtain user tokens from the email using the instruction from README.

Streaming speaker enhancement model list

2

I would like to know which streaming Speaker Enhancement models are currently supported by ESPNet. I only found `lichenda/wsj0_2mix_skim_small_causal` from the documents that can supprt streaming application. Would appreciate if...