Generating audio for text: '低下头,心想这下完了。...'
inputs:(1, 0)
inputs after padding:(1, 32000)
Traceback (most recent call last):
File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/torchaudio/_torchcodec.py", line 128, in load_with_torchcodec
audio_samples = decoder.get_all_samples()
^^^^^^^^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/torchcodec/decoders/_audio_decoder.py", line 108, in get_all_samples
return self.get_samples_played_in_range()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/torchcodec/decoders/_audio_decoder.py", line 137, in get_samples_played_in_range
frames, first_pts = core.get_frames_by_pts_in_range_audio(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/torch/_ops.py", line
......
too low.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/voxcpm/zipenhancer.py", line 67, in enhance
self._normalize_loudness(output_path)File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/voxcpm/zipenhancer.py", line 38, in _normalize_loudness
audio, sr = torchaudio.load(wav_path)
^^^^^^^^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/torchaudio/__init__.py", line 86, in load
return load_with_torchcodec(
^^^^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/torchaudio/_torchcodec.py", line 130, in load_with_torchcodec
raise RuntimeError(f"Failed to decode audio samples: {e}") from eRuntimeError: Failed to decode audio samples: No audio frames were decoded. This is probably because start_seconds is too high(0),or because stop_seconds(std::nullopt) is too low.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/gradio/queueing.py", line 759, in process_events
response = await route_utils.call_process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/gradio/route_utils.py", line 354, in call_process_api
output = await app.get_blocks().process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/gradio/blocks.py", line 2191, in process_api
result = await self.call_function(
^^^^^^^^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/gradio/blocks.py", line 1698, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/anyio/to_thread.py", line 61, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 2525, in run_sync_in_worker_thread
return await future
^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 986, in run
result = context.run(func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/gradio/utils.py", line 915, in wrapper
response = f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/video/VoxCPM/app.py", line 102, in generate_tts_audio
wav = current_model.generate(
^^^^^^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/voxcpm/core.py", line 130, in generate
return next(self._generate(*args, streaming=False, **kwargs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/voxcpm/core.py", line 196, in _generate
self.denoiser.enhance(prompt_wav_path, output_path=temp_prompt_wav_path)File "/Volumes/Ventoy/opt/miniconda3/envs/voxcpm/lib/python3.11/site-packages/voxcpm/zipenhancer.py", line 76, in enhance
raise RuntimeError(f"Audio denoising processing failed: {e}")RuntimeError: Audio denoising processing failed: Failed to decode audio samples: No audio frames were decoded. This is probably because start_seconds is too high(0),or because stop_seconds(std::nullopt) is too low.