atomicoo / fch-tts Goto Github PK

dear atomicoo：
There is error url : https://open-speech-data.oss-cn-hangzhou.aliyuncs.com, can not download data when run prepare_dataset.py

and could U pls share the the structure of directory “datasets” ，it's differece between your script
dataset_path = osp.join(datasets_path, dataset_dir)
wavfile_path = osp.join(dataset_path, "wavs")
melspec_path = osp.join(dataset_path, "mels")
and office data of BiaoBei
PhoneLabeling
ProsodyLabeling
Wave

如题，我已经同过其他方法生成语音。

比如tflite，比如换一个backbone是否有方法可以加速一下

Traceback (most recent call last):
File "/home/gaol/codes/Voices/FCH-TTS/train-parallel.py", line 69, in
loggers=loggers
File "/home/gaol/codes/Voices/FCH-TTS/helpers/trainer.py", line 319, in fit
valid_losses = self._validate(valid_loader)
File "/home/gaol/codes/Voices/FCH-TTS/helpers/trainer.py", line 419, in _validate
loss.item(), l1_loss.item(), ssim_loss.item(), drn_loss.item()
AttributeError: 'float' object has no attribute 'item'

我根据bbspeech.yaml的配置自己训练了中文模型，但是效果不好，不出声音。

GPU ：3060RTX12G
时长：24小时
数据集：Baker
BS：64

目前不知道是不是训练的步骤有问题，导致没有效果

untimeError: Calculated padded input size per channel: (5). Kernel size: (7). Kernel size can't be greater than actual input size

Env: （Nvidia T4，torch 1.9.0）
Tried the quick start with steps:
$ conda create -n ParallelTTS python=3.7.9
$ conda activate ParallelTTS
$ pip install -r requirements.txt
$ python synthesize.py
--checkpoint ./pretrained/ljspeech-parallel-epoch0100.pth
--melgan_checkpoint ./pretrained/ljspeech-melgan-epoch3200.pth
--input_texts ./samples/english/synthesize.txt
Failed with:

请问中文的模型开源了吗

请问有普通话的bbspeech-melgan-epoch*.pth 预训练模型吗 或者是要跑哪个脚本自己训练

如题