Open arnav-newzera opened 1 year ago
可以尝试用tts en的模型做finetune , 参看https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/examples/other/tts_finetune/tts3/README.md
感谢您的回复。我现在就试试。
我尝试了你所说的,但我在这个阶段遇到了错误:extract feature
/bin/bash: /home/newzera/anaconda3/envs/paddlespeech/lib/libtinfo.so.6: no version information available (required by /bin/bash)
check oov
get mfa result
align.py:60: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
Setting up corpus information...
Number of speakers in corpus: 1, average number of utterances per speaker: 602.0
/mnt/msd/users/arnav/PaddleSpeech/examples/other/tts_finetune/tts3/tools/montreal-forced-aligner/lib/aligner/models.py:87: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
Creating dictionary information...
Setting up training data...
Calculating MFCCs...
Traceback (most recent call last):
File "aligner/command_line/align.py", line 186, in <module>
File "aligner/command_line/align.py", line 142, in validate_args
File "aligner/command_line/align.py", line 94, in align_corpus
File "aligner/aligner/pretrained.py", line 74, in __init__
File "aligner/aligner/pretrained.py", line 122, in setup
File "aligner/aligner/base.py", line 89, in setup
File "aligner/corpus.py", line 979, in initialize_corpus
File "aligner/corpus.py", line 852, in create_mfccs
File "aligner/corpus.py", line 863, in _combine_feats
FileNotFoundError: [Errno 2] No such file or directory: '/home/arnav/Documents/MFA/newdir/train/mfcc/raw_mfcc.0.scp'
[68599] Failed to execute script align
generate durations.txt
extract feature
/home/newzera/anaconda3/envs/paddlespeech/lib/python3.7/site-packages/librosa/core/constantq.py:1059: DeprecationWarning: `np.complex` is a deprecated alias for the builtin `complex`. To silence this warning, use `complex` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.complex128` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
dtype=np.complex,
600 1
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████| 600/600 [00:00<00:00, 67646.43it/s]
Done
Traceback (most recent call last):
File "local/extract_feature.py", line 352, in <module>
replace_spkid=args.replace_spkid)
File "local/extract_feature.py", line 267, in extract_feature
vocab_speaker, dump_dir, "train")
File "local/extract_feature.py", line 160, in normalize
"energy": np.load,
File "/mnt/msd/users/arnav/PaddleSpeech/paddlespeech/t2s/datasets/data_table.py", line 47, in __init__
assert len(data) > 0, "This dataset has no examples"
AssertionError: This dataset has no examples
我查看了问题中的各种解决方案(小数据集是一个,但我的数据集有 1000+ wavs),(转换为 16 位,48khz)但错误仍然存在。
librosa==0.8.1 numpy==1.23.5
我安装了它,但它仍然显示相同的错误。
我尝试了你所说的,但我在这个阶段遇到了错误:extract feature
/bin/bash: /home/newzera/anaconda3/envs/paddlespeech/lib/libtinfo.so.6: no version information available (required by /bin/bash) check oov get mfa result align.py:60: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details. Setting up corpus information... Number of speakers in corpus: 1, average number of utterances per speaker: 602.0 /mnt/msd/users/arnav/PaddleSpeech/examples/other/tts_finetune/tts3/tools/montreal-forced-aligner/lib/aligner/models.py:87: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details. Creating dictionary information... Setting up training data... Calculating MFCCs... Traceback (most recent call last): File "aligner/command_line/align.py", line 186, in <module> File "aligner/command_line/align.py", line 142, in validate_args File "aligner/command_line/align.py", line 94, in align_corpus File "aligner/aligner/pretrained.py", line 74, in __init__ File "aligner/aligner/pretrained.py", line 122, in setup File "aligner/aligner/base.py", line 89, in setup File "aligner/corpus.py", line 979, in initialize_corpus File "aligner/corpus.py", line 852, in create_mfccs File "aligner/corpus.py", line 863, in _combine_feats FileNotFoundError: [Errno 2] No such file or directory: '/home/arnav/Documents/MFA/newdir/train/mfcc/raw_mfcc.0.scp' [68599] Failed to execute script align generate durations.txt extract feature /home/newzera/anaconda3/envs/paddlespeech/lib/python3.7/site-packages/librosa/core/constantq.py:1059: DeprecationWarning: `np.complex` is a deprecated alias for the builtin `complex`. To silence this warning, use `complex` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.complex128` here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations dtype=np.complex, 600 1 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████| 600/600 [00:00<00:00, 67646.43it/s] Done Traceback (most recent call last): File "local/extract_feature.py", line 352, in <module> replace_spkid=args.replace_spkid) File "local/extract_feature.py", line 267, in extract_feature vocab_speaker, dump_dir, "train") File "local/extract_feature.py", line 160, in normalize "energy": np.load, File "/mnt/msd/users/arnav/PaddleSpeech/paddlespeech/t2s/datasets/data_table.py", line 47, in __init__ assert len(data) > 0, "This dataset has no examples" AssertionError: This dataset has no examples
我查看了问题中的各种解决方案(小数据集是一个,但我的数据集有 1000+ wavs),(转换为 16 位,48khz)但错误仍然存在。 建议先用官方给的语音数据测试是否能跑通,如果可以,那就是自己数据集的问题了。
我在ttsfinetune的时候也遇到这个问题,看了一下代码发现mfa的结果是保存在./mfa_result下面的,但是读取的时候还有一个发音人id,所以要在mfa_result下面新建一个文件夹,把mfa的结果都扔进去
我安装了它,但它仍然显示相同的错误。
我在ttsfinetune的时候也遇到这个问题,看了一下代码发现mfa的结果是保存在./mfa_result下面的,但是读取的时候还有一个发音人id,所以要在mfa_result下面新建一个文件夹,把mfa的结果都扔进去
我安装了它,但它仍然显示相同的错误。
你好,我也遇到了同样的问题,请问新建的文件夹名字是什么,发音人id还是数据集的名字?
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
是否可以使用 paddlespeech 克隆英语语音? 我有一个说英语的人,我想用她的声音做 tts。
Is it possible to clone a english voice using paddlespeech? I have a english speaker, i want to do tts using her voice.