zyy-fc

The loss can not decrese

8

Thank you for sharing! I used the 4620 utterances from the training set of the TIMIT corpus as train set, and 119 types noise as train set. Besides, the 10...

Can your paper and code be used for linear array?

2

Thank you for sharing! I've read your paper and I wonder could your model and code be used for linear array?

details about the noisy_train.mat and target_train.mat

6

Thank you for your share! However, I want to know the details about how to constructi the "noisy_train" and "target_train". What is the meaning of "NUM_TOKENS" ? What about the...

the input to "bawn_pr_multi_gpu_train.py"

6

Thank you for your sharing! I am impressed by your work and I have two questions about the details of code. 1. To train the priori model, the input is...

[bug] encoding阶段生成的codec.txt, 无法直接读取？

1

按照提供的[encoding_decoding.sh](https://github.com/alibaba-damo-academy/FunCodec/blob/master/egs/LibriTTS/codec/encoding_decoding.sh)脚本，encoding阶段会生成codec.txt文件 这个文件的形式类似于： utts_id "空格" json.dumps(codecs) 这个形式无法被[read_text.py](https://github.com/alibaba-damo-academy/FunCodec/blob/master/funcodec/fileio/read_text.py)直接读取，需要改写“load_jsonl_trans_int”函数，如下 `def load_jsonl_trans_int(path: Union[Path, str]) -> Dict[str, np.ndarray]: d = read_2column_text(path) retval = {} for k, v in d.items(): try: value = json.loads(v) if isinstance(value,...

[Help]: The difference between the FAcodec pretrained model "FACodecEncoderV2" vs "FACodecEncoder"

1

Can you explain the difference between the FAcodec pretrained model "FACodecEncoderV2" vs "FACodecEncoder" ? Why using "FACodecEncoderV2" to do zero-shot TTS? Are these two difference from the training strategy or...

[Help]: Performance Inferior to Demo Showcase in terms of "FACodec: Voice Conversion Samples"

1

## Problem Overview I download the audios from the "[FACodec: Voice Conversion Samples](https://speechresearch.github.io/naturalspeech3/)" and I use the [python script shown in FACodec-README](https://github.com/open-mmlab/Amphion/tree/main/models/codec/ns3_codec) with pretrained model "FACodecEncoderV2/FACodecDecoderV2", but the voice conversion...

The paper of this code

2

Thank for your sharing! Could you tell me the name of article that you refer to in this code? Looking forward to your reply/

如题，想请教一下Speaker Encoder是怎么训练出来的，有参考的代码吗