Hi, I pass my trained xttsv2 model (vocab.json, model.pth, config.js) but it never run successfully:
I run this:
docker run -v /home/dev/xttsv2model:/app/tts_models --gpus=all -e COQUI_TOS_AGREED=1 --rm -p 8000:80 ghcr.io/coqui-ai/xtts-streaming-server:latest
and error occurred:
File "/app/main.py", line 41, in <module>
model.load_checkpoint(config, checkpoint_dir=model_path, eval=True, use_deepspeed=True if device == "cuda" else False)
File "/opt/conda/lib/python3.10/site-packages/TTS/tts/models/xtts.py", line 767, in load_checkpoint
self.tokenizer = VoiceBpeTokenizer(vocab_file=vocab_path)
File "/opt/conda/lib/python3.10/site-packages/TTS/tts/layers/xtts/tokenizer.py", line 596, in __init__
self.tokenizer = Tokenizer.from_file(vocab_file)
Exception: data did not match any variant of untagged enum ModelWrapper at line 41687 column 3