Both CPU version and GPU version docker images cannot handle the "tts_models/multilingual/multi-dataset/your_tts" model while voice cloning operation.
To Reproduce
Run the following command sudo docker run --rm --gpus all -v ~/tts-output:/root/tts-output ghcr.io/coqui-ai/tts --model_name "tts_models/multilingual/multi-dataset/your_tts" --language_idx en --speaker_wav "voices/ex.wav" --text "Hello hello hi hi." --out_path /root/tts-output/hello.wav --use_cuda true
see error
Traceback (most recent call last):
File "/usr/local/bin/tts", line 33, in <module>
sys.exit(load_entry_point('TTS', 'console_scripts', 'tts')())
File "/root/TTS/bin/synthesize.py", line 359, in main
> Model's license - CC BY-NC-ND 4.0
> Check https://creativecommons.org/licenses/by-nc-nd/4.0/ for more info.
if model_item["author"] == "fairseq" or isinstance(model_item["github_rls_url"], list):
KeyError: 'author'
Describe the bug
Both CPU version and GPU version docker images cannot handle the "tts_models/multilingual/multi-dataset/your_tts" model while voice cloning operation.
To Reproduce
sudo docker run --rm --gpus all -v ~/tts-output:/root/tts-output ghcr.io/coqui-ai/tts --model_name "tts_models/multilingual/multi-dataset/your_tts" --language_idx en --speaker_wav "voices/ex.wav" --text "Hello hello hi hi." --out_path /root/tts-output/hello.wav --use_cuda true
Expected behavior
The voice cloning operation goes through.
Logs
No response
Environment
Additional context
No response