Harry He

Hi, I think in "ns3codec" dir, we only provide pre-trained ckpt and inference codes of FAcodec, while in "FAcodec" dir, we provide training code for reimplement Facodec. Hope this help.

Hi, thank you so much for your attention.tion to our work! Please refer to the original Yodas dataset for the raw data and meta information: https://huggingface.co/datasets/espnet/yodas2

@RMSnow Thank you, Xueyao, for your detailed comments! @kenxxxxx Yuchen, please familiarize yourself with Git-based development and directly update your code on your fork so we can track your revision...

Thanks for the great reimplementation of Valle and your interesting thoughts about Emilia. It would be even better if you could compare the model you implemented with the original paper’s...

> * The output _seems_ fine? I'm extremely rusty with both, but the WER/SIM-O suggests it's fine. > * I am a bit skeptical about how SIM-O is calculated. *...

> Demo page updated with the correct SIM-O: > > * LibriVox-derived: 0.376 > * Emilia (EN): 0.520 > * Emilia (DE): 0.554 > * Emilia (FR): 0.469 > *...

> 使用清理/规范化的转录重新计算 WER，WER 实际上减少了（尤其是对于 Emilia JA/ZH）。 > 我仍然怀疑 WER/CER 是否非常低， just saw a intersting paper https://arxiv.org/pdf/2412.10117 which repots the objective evaluation result of almost all sota TTS models on the...