wwfcnu

在librispeech上测试model = AutoModel(model="paraformer-zh-streaming"),效果不理想

请问这个爬虫项目还在维护吗

1

如题

Is the FACodec training code open source?

这个数据集中有9000多小时无标签的数据，这部分数据在哪可以获取呢

Are there plans to open source the training data?

1

Are there plans to open source the training data?

datasets

2

Currently, there is only a link to the Emiia data. Do you have any plans to open source the processed audio data in the future?

automodel推理

3

``` from funasr import AutoModel # paraformer-zh is a multi-functional asr model # use vad, punc, spk or not as you need model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc", # spk_model="cam++", )...

**Describe the bug** libtorch解码的时候，占用内存不断增大 onnx解码正常

Notice: In order to resolve issues more efficiently, please raise issue following the template. （注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节） ## 🐛 Bug ` def _load_audio_ffmpeg(file: str, sr: int = 16000): """ Open an audio...