Traceback (most recent call last):
File ".../MOSS-TTS-Nano/app.py", line 218, in _run
result = self.runtime.warmup()
^^^^^^^^^^^^^^^^^^^^^
File ".../MOSS-TTS-Nano/moss_tts_nano_runtime.py", line 770, in warmup
return self.synthesize(
^^^^^^^^^^^^^^^^
File ".../MOSS-TTS-Nano/moss_tts_nano_runtime.py", line 547, in synthesize
result = model.inference(
^^^^^^^^^^^^^^^^
File ".../MOSS-TTS-Nano/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File ".../.cache/huggingface/modules/transformers_modules/OpenMOSS_hyphen_Team/MOSS_hyphen_TTS_hyphen_Nano/c3158a0fb0ff379ef79750129152b7730b5fb0f9/modeling_moss_tts_nano.py", line 2317, in inference
waveform, sample_rate = self._load_reference_audio(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".../.cache/huggingface/modules/transformers_modules/OpenMOSS_hyphen_Team/MOSS_hyphen_TTS_hyphen_Nano/c3158a0fb0ff379ef79750129152b7730b5fb0f9/modeling_moss_tts_nano.py", line 1613, in _load_reference_audio
waveform, sample_rate = torchaudio.load(str(reference_audio_path))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".../MOSS-TTS-Nano/.venv/lib/python3.12/site-packages/torchaudio/_backend/utils.py", line 204, in load
backend = dispatcher(uri, format, backend)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".../MOSS-TTS-Nano/.venv/lib/python3.12/site-packages/torchaudio/_backend/utils.py", line 116, in dispatcher
raise RuntimeError(f"Couldn't find appropriate backend to handle uri {uri} and format {format}.")
RuntimeError: Couldn't find appropriate backend to handle uri .../MOSS-TTS-Nano/assets/audio/zh_1.wav and format None.
I get this error when running
app.py. The demo is currently unusable.