coqui-ai / TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
http://coqui.ai
Mozilla Public License 2.0
34.53k stars 4.19k forks source link

chinese voice conversion failed #1900

Closed kdtiankong closed 2 years ago

kdtiankong commented 2 years ago

Describe the bug

tts --model_name tts_models/multilingual/multi-dataset/your_tts --encoder_path model_se.pth.tar --encoder_config config_se.json --speaker_wav D:\voice\TTS-0.7.1\TTS-model\dst.wav --reference_wav D:\voice\TTS-0.7.1\TTS-model\ref.wav --language_idx "zh-cn"

Traceback (most recent call last): File "C:\ProgramData\Anaconda3\envs\tts\Scripts\tts-script.py", line 33, in sys.exit(load_entry_point('TTS', 'console_scripts', 'tts')()) File "d:\voice\tts-0.7.1\tts-0.7.1\TTS\bin\synthesize.py", line 350, in main wav = synthesizer.tts( File "d:\voice\tts-0.7.1\tts-0.7.1\TTS\utils\synthesizer.py", line 247, in tts language_id = self.tts_model.language_manager.ids[language_name] KeyError: 'zh-CN'

english module version is ok. chinese module is failed!!!

To Reproduce

tts --model_name tts_models/multilingual/multi-dataset/your_tts --encoder_path model_se.pth.tar --encoder_config config_se.json --speaker_wav D:\voice\TTS-0.7.1\TTS-model\cyw-out-002.wav --reference_wav D:\voice\TTS-0.7.1\TTS-model\cyw-out-002.wav --language_idx "zh-CN"

Expected behavior

No response

Logs

No response

Environment

{
    "Packages": {
        "PyTorch_debug": false,
        "PyTorch_version": "1.11.0+cpu",
        "TTS": "0.8.0",
        "numpy": "1.21.6"
    },
    "System": {
        "OS": "Linux",
        "architecture": [
            "64bit",
            ""
        ],
        "processor": "x86_64",
        "python": "3.8.10",
        "version": "#91-Ubuntu SMP Thu Jul 15 19:09:17 UTC 2021"
    }
}

Additional context

No response

xiaocdh commented 1 year ago

The problem still exists