Colab error, huggingface space down

[ThatDocBoi]

When I run the colab, upon re-running after the restart I get this error:

Collecting pyannote.database>=5.0.1 (from pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached pyannote.database-5.1.0-py3-none-any.whl.metadata (1.2 kB)
Collecting pyannote.metrics>=3.2 (from pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached pyannote.metrics-3.2.1-py3-none-any.whl.metadata (1.3 kB)
Collecting pyannote.pipeline>=3.0.1 (from pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached pyannote.pipeline-3.0.1-py3-none-any.whl.metadata (897 bytes)
Collecting pytorch-metric-learning>=2.1.0 (from pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached pytorch_metric_learning-2.7.0-py3-none-any.whl.metadata (17 kB)
Requirement already satisfied: rich>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (13.9.4)
Collecting semver>=3.0.0 (from pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached semver-3.0.2-py3-none-any.whl.metadata (5.0 kB)
Requirement already satisfied: soundfile>=0.12.1 in /usr/local/lib/python3.10/dist-packages (from pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (0.12.1)
Collecting speechbrain>=0.5.14 (from pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached speechbrain-1.0.2-py3-none-any.whl.metadata (23 kB)
Collecting tensorboardX>=2.6 (from pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached tensorboardX-2.6.2.2-py2.py3-none-any.whl.metadata (5.8 kB)
Collecting torch-audiomentations>=0.11.0 (from pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached torch_audiomentations-0.11.1-py3-none-any.whl.metadata (14 kB)
Requirement already satisfied: torchmetrics>=0.11.0 in /usr/local/lib/python3.10/dist-packages (from pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (1.6.0)
Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (0.4)
Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (4.23.0)
Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (0.12.1)
Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.10/dist-packages (from BeautifulSoup4>=4.5.1->aeneas>=1.7.3.0->-r /content/VoiceCraft/gradio_requirements.txt (line 4)) (2.6)
Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (1.3.1)
Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (0.12.1)
Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (4.55.0)
Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (1.4.7)
Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (3.2.0)
Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (2024.2)
Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (2024.2)
Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests~=2.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (3.4.0)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests~=2.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (3.10)
Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests~=2.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (2.2.3)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests~=2.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (2024.8.30)
Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->openai-whisper>=20231117->-r /content/VoiceCraft/gradio_requirements.txt (line 3)) (3.4.2)
Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.10/dist-packages (from torch->openai-whisper>=20231117->-r /content/VoiceCraft/gradio_requirements.txt (line 3)) (1.13.1)
Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy==1.13.1->torch->openai-whisper>=20231117->-r /content/VoiceCraft/gradio_requirements.txt (line 3)) (1.3.0)
Requirement already satisfied: h11>=0.8 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (0.14.0)
Requirement already satisfied: starlette<0.42.0,>=0.40.0 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (0.41.3)
Collecting ctranslate2<5,>=4.0 (from faster-whisper->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached ctranslate2-4.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (10 kB)
Requirement already satisfied: tokenizers<1,>=0.13 in /usr/local/lib/python3.10/dist-packages (from faster-whisper->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (0.20.3)
Collecting onnxruntime<2,>=1.14 (from faster-whisper->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached onnxruntime-1.20.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (4.5 kB)
Requirement already satisfied: av>=11 in /usr/local/lib/python3.10/dist-packages (from faster-whisper->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (13.1.0)
Requirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (3.7.1)
Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (1.0.7)
Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (1.3.1)
Requirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.10/dist-packages (from numba->openai-whisper>=20231117->-r /content/VoiceCraft/gradio_requirements.txt (line 3)) (0.43.0)
INFO: pip is looking at multiple versions of transformers to determine which version is compatible with other requirements. This could take a while.
Collecting transformers (from whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached transformers-4.46.3-py3-none-any.whl.metadata (44 kB)
  Using cached transformers-4.46.1-py3-none-any.whl.metadata (44 kB)
  Using cached transformers-4.45.2-py3-none-any.whl.metadata (44 kB)
  Using cached transformers-4.45.1-py3-none-any.whl.metadata (44 kB)
  Using cached transformers-4.45.0-py3-none-any.whl.metadata (44 kB)
  Using cached transformers-4.44.2-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.44.1-py3-none-any.whl.metadata (43 kB)
INFO: pip is still looking at multiple versions of transformers to determine which version is compatible with other requirements. This could take a while.
  Using cached transformers-4.44.0-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.43.4-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.43.3-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.43.2-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.43.1-py3-none-any.whl.metadata (43 kB)
INFO: This is taking longer than usual. You might need to provide the dependency resolver with stricter constraints to reduce runtime. See https://pip.pypa.io/warnings/backtracking for guidance. If you want to abort this run, press Ctrl + C.
  Using cached transformers-4.43.0-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.42.4-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.42.3-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.42.2-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.42.1-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.42.0-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.41.2-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.41.1-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.41.0-py3-none-any.whl.metadata (43 kB)
  Using cached transformers-4.40.2-py3-none-any.whl.metadata (137 kB)
Collecting tokenizers<1,>=0.13 (from faster-whisper->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached tokenizers-0.19.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)
Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (0.4.5)
Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (24.2.0)
Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (2024.10.1)
Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (0.35.1)
Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (0.21.0)
Requirement already satisfied: lightning-utilities<2.0,>=0.10.0 in /usr/local/lib/python3.10/dist-packages (from lightning>=2.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (0.11.9)
Collecting pytorch-lightning (from lightning>=2.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached pytorch_lightning-2.4.0-py3-none-any.whl.metadata (21 kB)
Requirement already satisfied: antlr4-python3-runtime==4.9.* in /usr/local/lib/python3.10/dist-packages (from omegaconf<3.0,>=2.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (4.9.3)
Collecting coloredlogs (from onnxruntime<2,>=1.14->faster-whisper->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached coloredlogs-15.0.1-py2.py3-none-any.whl.metadata (12 kB)
Requirement already satisfied: flatbuffers in /usr/local/lib/python3.10/dist-packages (from onnxruntime<2,>=1.14->faster-whisper->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (24.3.25)
Requirement already satisfied: protobuf in /usr/local/lib/python3.10/dist-packages (from onnxruntime<2,>=1.14->faster-whisper->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (4.25.5)
Collecting sortedcontainers>=2.0.4 (from pyannote.core>=5.0.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached sortedcontainers-2.4.0-py2.py3-none-any.whl.metadata (10 kB)
Requirement already satisfied: scipy>=1.1 in /usr/local/lib/python3.10/dist-packages (from pyannote.core>=5.0.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (1.13.1)
Collecting typer>=0.12.1 (from pyannote.database>=5.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached typer-0.13.1-py3-none-any.whl.metadata (15 kB)
Requirement already satisfied: scikit-learn>=0.17.1 in /usr/local/lib/python3.10/dist-packages (from pyannote.metrics>=3.2->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (1.5.2)
Requirement already satisfied: tabulate>=0.7.7 in /usr/local/lib/python3.10/dist-packages (from pyannote.metrics>=3.2->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (0.9.0)
Collecting optuna>=3.1 (from pyannote.pipeline>=3.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached optuna-4.1.0-py3-none-any.whl.metadata (16 kB)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib~=3.0->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (1.16.0)
Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=12.0.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (3.0.0)
Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=12.0.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (2.18.0)
Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.10/dist-packages (from soundfile>=0.12.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (1.17.1)
Collecting hyperpyyaml (from speechbrain>=0.5.14->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached HyperPyYAML-1.2.2-py3-none-any.whl.metadata (7.6 kB)
Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (from speechbrain>=0.5.14->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (0.2.0)
Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->httpx->gradio==3.50.2->-r /content/VoiceCraft/gradio_requirements.txt (line 1)) (1.2.2)
Requirement already satisfied: julius<0.3,>=0.2.3 in /usr/local/lib/python3.10/dist-packages (from torch-audiomentations>=0.11.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (0.2.7)
Requirement already satisfied: librosa>=0.6.0 in /usr/local/lib/python3.10/dist-packages (from torch-audiomentations>=0.11.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (0.10.2.post1)
Collecting torch-pitch-shift>=1.2.2 (from torch-audiomentations>=0.11.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached torch_pitch_shift-1.2.5-py3-none-any.whl.metadata (2.5 kB)
Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.0->soundfile>=0.12.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (2.22)
Requirement already satisfied: aiohttp!=4.0.0a0,!=4.0.0a1 in /usr/local/lib/python3.10/dist-packages (from fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (3.11.2)
Requirement already satisfied: audioread>=2.1.9 in /usr/local/lib/python3.10/dist-packages (from librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (3.0.1)
Requirement already satisfied: decorator>=4.3.0 in /usr/local/lib/python3.10/dist-packages (from librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (4.4.2)
Requirement already satisfied: pooch>=1.1 in /usr/local/lib/python3.10/dist-packages (from librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (1.8.2)
Requirement already satisfied: soxr>=0.3.2 in /usr/local/lib/python3.10/dist-packages (from librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (0.5.0.post1)
Requirement already satisfied: lazy-loader>=0.1 in /usr/local/lib/python3.10/dist-packages (from librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (0.4)
Requirement already satisfied: msgpack>=1.0 in /usr/local/lib/python3.10/dist-packages (from librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (1.1.0)
Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=12.0.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (0.1.2)
Collecting alembic>=1.5.0 (from optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached alembic-1.14.0-py3-none-any.whl.metadata (7.4 kB)
Requirement already satisfied: colorlog in /usr/local/lib/python3.10/dist-packages (from optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (6.9.0)
Requirement already satisfied: sqlalchemy>=1.4.2 in /usr/local/lib/python3.10/dist-packages (from optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (2.0.36)
Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.17.1->pyannote.metrics>=3.2->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (3.5.0)
Collecting primePy>=1.3 (from torch-pitch-shift>=1.2.2->torch-audiomentations>=0.11.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached primePy-1.3-py3-none-any.whl.metadata (4.8 kB)
Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer>=0.12.1->pyannote.database>=5.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (1.5.4)
Collecting humanfriendly>=9.1 (from coloredlogs->onnxruntime<2,>=1.14->faster-whisper->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached humanfriendly-10.0-py2.py3-none-any.whl.metadata (9.2 kB)
Collecting ruamel.yaml>=0.17.28 (from hyperpyyaml->speechbrain>=0.5.14->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached ruamel.yaml-0.18.6-py3-none-any.whl.metadata (23 kB)
Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (2.4.3)
Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (1.3.1)
Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (1.5.0)
Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (6.1.0)
Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (0.2.0)
Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (1.17.2)
Requirement already satisfied: async-timeout<6.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (4.0.3)
Collecting Mako (from alembic>=1.5.0->optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached Mako-1.3.6-py3-none-any.whl.metadata (2.9 kB)
Requirement already satisfied: platformdirs>=2.5.0 in /usr/local/lib/python3.10/dist-packages (from pooch>=1.1->librosa>=0.6.0->torch-audiomentations>=0.11.0->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (4.3.6)
Collecting ruamel.yaml.clib>=0.2.7 (from ruamel.yaml>=0.17.28->hyperpyyaml->speechbrain>=0.5.14->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5))
  Using cached ruamel.yaml.clib-0.2.12-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.7 kB)
Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.10/dist-packages (from sqlalchemy>=1.4.2->optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote.audio==3.1.1->whisperx>=3.1.1->-r /content/VoiceCraft/gradio_requirements.txt (line 5)) (3.1.1)
Using cached huggingface_hub-0.22.2-py3-none-any.whl (388 kB)
Using cached whisperx-3.1.6-py3-none-any.whl (44 kB)
Using cached pyannote.audio-3.1.1-py2.py3-none-any.whl (208 kB)
Using cached triton-3.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (209.5 MB)
Using cached faster_whisper-1.1.0-py3-none-any.whl (1.1 MB)
Using cached tiktoken-0.8.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)
Using cached transformers-4.40.2-py3-none-any.whl (9.0 MB)
Using cached asteroid_filterbanks-0.4.0-py3-none-any.whl (29 kB)
Using cached ctranslate2-4.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (38.4 MB)
Using cached lightning-2.4.0-py3-none-any.whl (810 kB)
Using cached onnxruntime-1.20.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (13.3 MB)
Using cached pyannote.core-5.0.0-py3-none-any.whl (58 kB)
Using cached pyannote.database-5.1.0-py3-none-any.whl (48 kB)
Using cached pyannote.metrics-3.2.1-py3-none-any.whl (51 kB)
Using cached pyannote.pipeline-3.0.1-py3-none-any.whl (31 kB)
Using cached pytorch_metric_learning-2.7.0-py3-none-any.whl (120 kB)
Using cached semver-3.0.2-py3-none-any.whl (17 kB)
Using cached speechbrain-1.0.2-py3-none-any.whl (824 kB)
Using cached tensorboardX-2.6.2.2-py2.py3-none-any.whl (101 kB)
Using cached tokenizers-0.19.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.6 MB)
Using cached torch_audiomentations-0.11.1-py3-none-any.whl (50 kB)
Using cached optuna-4.1.0-py3-none-any.whl (364 kB)
Using cached sortedcontainers-2.4.0-py2.py3-none-any.whl (29 kB)
Using cached torch_pitch_shift-1.2.5-py3-none-any.whl (5.0 kB)
Using cached typer-0.13.1-py3-none-any.whl (44 kB)
Using cached coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)
Using cached HyperPyYAML-1.2.2-py3-none-any.whl (16 kB)
Using cached pytorch_lightning-2.4.0-py3-none-any.whl (815 kB)
Using cached alembic-1.14.0-py3-none-any.whl (233 kB)
Using cached humanfriendly-10.0-py2.py3-none-any.whl (86 kB)
Using cached primePy-1.3-py3-none-any.whl (4.0 kB)
Using cached ruamel.yaml-0.18.6-py3-none-any.whl (117 kB)
Using cached ruamel.yaml.clib-0.2.12-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (722 kB)
Using cached Mako-1.3.6-py3-none-any.whl (78 kB)
Building wheels for collected packages: aeneas
  error: subprocess-exited-with-error
  
  × python setup.py bdist_wheel did not run successfully.
  │ exit code: 1
  ╰─> See above for output.
  
  note: This error originates from a subprocess, and is likely not a problem with pip.
  Building wheel for aeneas (setup.py) ... error
  ERROR: Failed building wheel for aeneas
  Running setup.py clean for aeneas
Failed to build aeneas
ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (aeneas)
Requirement already satisfied: typer==0.7.0 in /usr/local/lib/python3.10/dist-packages (0.7.0)
Requirement already satisfied: click<9.0.0,>=7.1.1 in /usr/local/lib/python3.10/dist-packages (from typer==0.7.0) (8.1.7)

The huggingface demo shows:

build error
Job failed with exit code: 1
Build logs:

===== Build Queued at 2024-05-09 07:52:28 / Commit SHA: 0c27362 =====

I also tried Kijai's old comyfui node but it is not working as well and tts-generation-webui doesn't support this text to voice model. Any way at all to run this without paying for replicate?