-
This is a really good project. I was wondering if WavLM is supported in the project, I wanted to run a voice conversation model in the browser, also if Hifi-gan for voice synthesis.
-
你好，我在使用`DiffuseStyleGesture+`进行推理时，写bvh出现了问题，涉及到的代码为[code](https://github.com/YoungSeng/DiffuseStyleGesture/blob/master/BEAT-TWH-main/process/pymo/writers.py#L57), 列表`self.motions_`前6个元组的形状为（num_frame…
-
Share your Chinese synthesis results or mandrain model training questions.
-
Hi,
I would like to obtain inferences on audio files using a model trained using wavlm features (following the asr2 recipe). I am able to directly pass the raw audio tensor to `espnet2.bin.asr_infe…
-
你好！ 请问有评估指标的代码吗？
223d updated
11 months ago
-
Great repo! Ran some tests with it and it sounds good for speech, but the limited testing I did for singing didn't sound too great. Is this expected / is there a way to adapt it to work well with sing…
-
Dear author, your article and code are very helpful to me, and I will also cite your article in my paper later. Could you please upload the data processing and training part about meld data set? I can…
MF-XU updated
9 months ago
-
您好，
这个工作非常的棒，但是我想知道你们是否有将 WavLM 模型添加到该库中的打算？
-
Thanks for your hard work. I wonder if you will share the training log, facilitating us to refer to it?
gancx updated
10 months ago
-
### 🐛 Describe the bug
When comparing the WAVLM_BASE model from the Torchaudio pipeline with the one HuggingFace provides (here : https://huggingface.co/microsoft/wavlm-base), it appears that the r…