Hey guys,
I’m not sure this is the right place to ask this question, and I hope it isn’t too stupid. I’ve installed Mozilla TTS on an Ubuntu system with Python 3.10 in a virtualenv box (via pip) just to play around with it. I’ve followed (I think) the instructions but on attempting to use one of the inbuilt models/vocoders for the first time, I get the following message:
> Downloading model to /home/redacted/.local/share/tts/vocoder_models--universal--libri-tts--wavegrad
100%|███████████████████████████████████████████████████████████████████████████████████████| 175M/175M [00:53<00:00, 3.28MiB/s]
> Model's license - MPL
> Check https://www.mozilla.org/en-US/MPL/2.0/ for more info.
Traceback (most recent call last):
File "/home/redacted/workspace/mozilla-tts/env-mozilla-tts/bin/tts", line 8, in <module>
sys.exit(main())
File "/home/redacted/workspace/mozilla-tts/env-mozilla-tts/lib/python3.10/site-packages/TTS/bin/synthesize.py", line 371, in main
synthesizer = Synthesizer(
File "/home/redacted/workspace/mozilla-tts/env-mozilla-tts/lib/python3.10/site-packages/TTS/utils/synthesizer.py", line 86, in __init__
self._load_tts(tts_checkpoint, tts_config_path, use_cuda)
File "/home/redacted/workspace/mozilla-tts/env-mozilla-tts/lib/python3.10/site-packages/TTS/utils/synthesizer.py", line 144, in _load_tts
self.tts_config = load_config(tts_config_path)
File "/home/redacted/workspace/mozilla-tts/env-mozilla-tts/lib/python3.10/site-packages/TTS/config/__init__.py", line 79, in load_config
ext = os.path.splitext(config_path)[1]
File "/usr/lib/python3.10/posixpath.py", line 118, in splitext
p = os.fspath(p)
TypeError: expected str, bytes or os.PathLike object, not NoneType
I used the command:
tts --text "Test speech" \
--model_path "tts_models/multilingual/multi-dataset/your_tts" \
--vocoder_name "vocoder_models/universal/libri-tts/wavegrad" \
--out_path /home/redacted/workspace/mozilla-tts/output
It seems to be looking for a config file? Did I miss some obvious part of the installation?
Any guidance would be appreciated.