PaddleSpeech: Parallel WaveGAN with CSMSC error

我参考这个案例进行训练 https://github.com/PaddlePaddle/PaddleSpeech/tree/19f67e1f564f1dcd49b89159b39bb4a34b7b6cdd/examples/csmsc/voc1

已经下载好了数据集

(base) root@ff21c21bf0ea:/opt/PaddleSpeech/examples/csmsc/voc1# ll ~/datasets/
total 1156
drwxr-sr-x 3 root   users 593920 Feb 25 09:31 ./
drwsrwsr-x 1 jovyan users   4096 Feb 28 06:06 ../
drwxr-sr-x 3 root   users 577536 Feb 25 09:31 BZNSYP/

baker_alignment_tone.tar.gz文件也解压到了当前的目录中 已经满足了README文件中的条件

Assume the path to the dataset is ~/datasets/BZNSYP. Assume the path to the MFA result of CSMSC is ./baker_alignment_tone. Run the command below to

source path.
preprocess the dataset.
train the model.
synthesize wavs.
synthesize waveform from metadata.jsonl.
./run.sh

在运行run.sh 的时候,我得到了下面的错误信息,我不知道该怎样解决

(base) root@ff21c21bf0ea:/opt/PaddleSpeech/examples/csmsc/voc1# ./run.sh
Generate durations.txt from MFA results ...
Extract features ...
/home/jovyan/datasets/BZNSYP
Get features' stats ...
Traceback (most recent call last):
  File "/opt/PaddleSpeech/utils/compute_statistics.py", line 109, in <module>
    main()
  File "/opt/PaddleSpeech/utils/compute_statistics.py", line 84, in main
    with jsonlines.open(args.metadata, 'r') as reader:
  File "/opt/conda/lib/python3.8/site-packages/jsonlines/jsonlines.py", line 623, in open
    fp = builtins.open(file, mode=mode + "t", encoding=encoding)
FileNotFoundError: [Errno 2] No such file or directory: 'dump/train/raw/metadata.jsonl'
Normalize ...
Traceback (most recent call last):
  File "/opt/PaddleSpeech/paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/../normalize.py", line 133, in <module>
    main()
  File "/opt/PaddleSpeech/paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/../normalize.py", line 81, in main
    with jsonlines.open(args.metadata, 'r') as reader:
  File "/opt/conda/lib/python3.8/site-packages/jsonlines/jsonlines.py", line 623, in open
    fp = builtins.open(file, mode=mode + "t", encoding=encoding)
FileNotFoundError: [Errno 2] No such file or directory: 'dump/train/raw/metadata.jsonl'
Traceback (most recent call last):
  File "/opt/PaddleSpeech/paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/../normalize.py", line 133, in <module>
    main()
  File "/opt/PaddleSpeech/paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/../normalize.py", line 81, in main
    with jsonlines.open(args.metadata, 'r') as reader:
  File "/opt/conda/lib/python3.8/site-packages/jsonlines/jsonlines.py", line 623, in open
    fp = builtins.open(file, mode=mode + "t", encoding=encoding)
FileNotFoundError: [Errno 2] No such file or directory: 'dump/dev/raw/metadata.jsonl'
Traceback (most recent call last):
  File "/opt/PaddleSpeech/paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/../normalize.py", line 133, in <module>
    main()
  File "/opt/PaddleSpeech/paddlespeech/t2s/exps/gan_vocoder/parallelwave_gan/../normalize.py", line 81, in main
    with jsonlines.open(args.metadata, 'r') as reader:
  File "/opt/conda/lib/python3.8/site-packages/jsonlines/jsonlines.py", line 623, in open
    fp = builtins.open(file, mode=mode + "t", encoding=encoding)
FileNotFoundError: [Errno 2] No such file or directory: 'dump/test/raw/metadata.jsonl'

dump/train/raw/metadata.jsonl 应该是run.sh 生成的吧,但实际上并没有生成这个文件

About this issue

  • Original URL
  • State: closed
  • Created 2 years ago
  • Comments: 17

Most upvoted comments

我也遇到这个问题,我这边是 csmsc 数据集的问题,使用 rar 解压下来直接变成一个文件夹,乱套了,可以尝试自己在电脑上解压,然后压缩到 zip 里面再传输到服务器上