There is a tutorial of korean version of coqui_tts.(not written by coqui-ai)
tutorial link : https://colab.research.google.com/drive/1hv37sT7Pq-qKZe9Ihbbp5XZ-A9tsURli?usp=sharing
Executed command
!tts \ --text "$inputText" \ --model_path glowtts_korea/checkpoint.pth.tar \ --config_path glowtts_korea/config.json \ --out_path output.wav \ --vocoder_path mbmelgan_korea/checkpoint.pth.tar \ --vocoder_config_path mbmelgan_korea/config.json
Result
` > Using model: glow_tts
Setting up Audio Processor...
| > sample_rate:22050
| > resample:False
| > num_mels:80
| > log_func:np.log10
| > min_level_db:-100
| > frame_shift_ms:None
| > frame_length_ms:None
| > ref_level_db:20
| > fft_size:1024
| > power:1.5
| > preemphasis:0.0
| > griffin_lim_iters:60
| > signal_norm:True
| > symmetric_norm:True
| > mel_fmin:0
| > mel_fmax:None
| > pitch_fmin:0.0
| > pitch_fmax:640.0
| > spec_gain:20.0
| > stft_pad_mode:reflect
| > max_norm:4.0
| > clip_norm:True
| > do_trim_silence:True
| > trim_db:45
| > do_sound_norm:False
| > do_amp_to_db_linear:True
| > do_amp_to_db_mel:True
| > do_rms_norm:False
| > db_level:None
| > stats_path:None
| > base:10
| > hop_length:256
| > win_length:1024
Traceback (most recent call last):
File "/usr/local/bin/tts", line 8, in
sys.exit(main())
File "/usr/local/lib/python3.7/dist-packages/TTS/bin/synthesize.py", line 318, in main
args.use_cuda,
File "/usr/local/lib/python3.7/dist-packages/TTS/utils/synthesizer.py", line 76, in init
self._load_tts(tts_checkpoint, tts_config_path, use_cuda)
File "/usr/local/lib/python3.7/dist-packages/TTS/utils/synthesizer.py", line 113, in _load_tts
self.tts_model = setup_tts_model(config=self.tts_config)
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/models/init.py", line 13, in setup_model
model = MyModel.init_from_config(config, samples)
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/models/glow_tts.py", line 556, in init_from_config
tokenizer, new_config = TTSTokenizer.init_from_config(config)
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/utils/text/tokenizer.py", line 174, in init_from_config
characters, new_config = Graphemes().init_from_config(config)
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/utils/text/characters.py", line 454, in init_from_config
is_sorted=config.characters["is_sorted"],
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/utils/text/characters.py", line 433, in init
super().init(characters, punctuations, pad, eos, bos, blank, is_unique, is_sorted)
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/utils/text/characters.py", line 167, in init
self._create_vocab()
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/utils/text/characters.py", line 263, in _create_vocab
), f" [!] There are duplicate characters in the character set. {duplicates}"
AssertionError: [!] There are duplicate characters in the character set. {'(', '!', "'", ' ', '?', ',', ')', '-', ':', ';', '.'}
/usr/local/lib/python3.7/dist-packages/librosa/core/audio.py:162: UserWarning: PySoundFile failed. Trying audioread instead.
warnings.warn("PySoundFile failed. Trying audioread instead.")`
In the config.json, it contains {'(', '!', "'", ' ', '?', ',', ')', '-', ':', ';', '.'} and korean unicode characters.
I saw that this error had been issued(https://github.com/coqui-ai/TTS/issues/1693), but I can't solve the error by the answer in the previous issue.(reinstall or "rm -rf ~/.local/share/tts/tts_models--multilingual--multi-dataset--your_tts/")
You can see this command on the link.
!tts \ --text "$inputText" \ --model_path glowtts_korea/checkpoint.pth.tar \ --config_path glowtts_korea/config.json \ --out_path output.wav \ --vocoder_path mbmelgan_korea/checkpoint.pth.tar \ --vocoder_config_path mbmelgan_korea/config.json
Expected behavior
save output.wav
Logs
Traceback (most recent call last):
File "/usr/local/bin/tts", line 8, in <module>
sys.exit(main())
File "/usr/local/lib/python3.7/dist-packages/TTS/bin/synthesize.py", line 318, in main
args.use_cuda,
File "/usr/local/lib/python3.7/dist-packages/TTS/utils/synthesizer.py", line 76, in __init__
self._load_tts(tts_checkpoint, tts_config_path, use_cuda)
File "/usr/local/lib/python3.7/dist-packages/TTS/utils/synthesizer.py", line 113, in _load_tts
self.tts_model = setup_tts_model(config=self.tts_config)
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/models/__init__.py", line 13, in setup_model
model = MyModel.init_from_config(config, samples)
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/models/glow_tts.py", line 556, in init_from_config
tokenizer, new_config = TTSTokenizer.init_from_config(config)
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/utils/text/tokenizer.py", line 174, in init_from_config
characters, new_config = Graphemes().init_from_config(config)
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/utils/text/characters.py", line 454, in init_from_config
is_sorted=config.characters["is_sorted"],
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/utils/text/characters.py", line 433, in __init__
super().__init__(characters, punctuations, pad, eos, bos, blank, is_unique, is_sorted)
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/utils/text/characters.py", line 167, in __init__
self._create_vocab()
File "/usr/local/lib/python3.7/dist-packages/TTS/tts/utils/text/characters.py", line 263, in _create_vocab
), f" [!] There are duplicate characters in the character set. {duplicates}"
AssertionError: [!] There are duplicate characters in the character set. {'(', '!', "'", ' ', '?', ',', ')', '-', ':', ';', '.'}
/usr/local/lib/python3.7/dist-packages/librosa/core/audio.py:162: UserWarning: PySoundFile failed. Trying audioread instead.
warnings.warn("PySoundFile failed. Trying audioread instead.")
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/librosa/core/audio.py in load(path, sr, mono, offset, duration, dtype, res_type)
145 try:
--> 146 with sf.SoundFile(path) as sf_desc:
147 sr_native = sf_desc.samplerate
8 frames
RuntimeError: Error opening 'output.wav': System error.
During handling of the above exception, another exception occurred:
FileNotFoundError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/audioread/rawread.py in __init__(self, filename)
60 """
61 def __init__(self, filename):
---> 62 self._fh = open(filename, 'rb')
63
64 try:
FileNotFoundError: [Errno 2] No such file or directory: 'output.wav'
Describe the bug
There is a tutorial of korean version of coqui_tts.(not written by coqui-ai) tutorial link : https://colab.research.google.com/drive/1hv37sT7Pq-qKZe9Ihbbp5XZ-A9tsURli?usp=sharing Executed command
!tts \ --text "$inputText" \ --model_path glowtts_korea/checkpoint.pth.tar \ --config_path glowtts_korea/config.json \ --out_path output.wav \ --vocoder_path mbmelgan_korea/checkpoint.pth.tar \ --vocoder_config_path mbmelgan_korea/config.json
Result ` > Using model: glow_tts
In the config.json, it contains {'(', '!', "'", ' ', '?', ',', ')', '-', ':', ';', '.'} and korean unicode characters. I saw that this error had been issued(https://github.com/coqui-ai/TTS/issues/1693), but I can't solve the error by the answer in the previous issue.(reinstall or "rm -rf ~/.local/share/tts/tts_models--multilingual--multi-dataset--your_tts/")
To Reproduce
link : https://colab.research.google.com/drive/1hv37sT7Pq-qKZe9Ihbbp5XZ-A9tsURli?usp=sharing
Run top three cells in the link
You can see this command on the link.
!tts \ --text "$inputText" \ --model_path glowtts_korea/checkpoint.pth.tar \ --config_path glowtts_korea/config.json \ --out_path output.wav \ --vocoder_path mbmelgan_korea/checkpoint.pth.tar \ --vocoder_config_path mbmelgan_korea/config.json
Expected behavior
save output.wav
Logs
Environment
Additional context
No response