[Bug] XTTS Finetuning - xtts_demo.py - Collab

[kabelklaus]

Describe the bug

starting the process of train with a .wav file

To Reproduce

1. Start xtts_demo.py
2. klick on the link for gradio
3. move a .wav to the file section
4. start the first step of the process

Expected behavior

When I upload a .wav file and start the process in gradio, I would like to come to the next step (step 2) in the finetune training.

Logs

The data processing was interrupted due an error !! Please check the console to verify the full error message! Error summary: Traceback (most recent call last): File "/content/TTS/TTS/demos/xtts_ft_demo/xtts_demo.py", line 215, in preprocess_dataset train_meta, eval_meta, audio_total_size = format_audio_list(audio_path, target_language=language, out_path=out_path, gradio_progress=progress) File "/content/TTS/TTS/demos/xtts_ft_demo/utils/formatter.py", line 75, in format_audio_list segments = list(segments) File "/usr/local/lib/python3.10/dist-packages/faster_whisper/transcribe.py", line 426, in generate_segments encoder_output = self.encode(segment) File "/usr/local/lib/python3.10/dist-packages/faster_whisper/transcribe.py", line 610, in encode return self.model.encode(features, to_cpu=to_cpu) RuntimeError: Library libcublas.so.11 is not found or cannot be loaded

Environment

# Installiere die benötigten CUDA-Bibliotheken
!apt-get update
!apt-get install -y wget
!wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin
!mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600
!wget https://developer.download.nvidia.com/compute/cuda/12.2.0/local_installers/cuda-repo-ubuntu2004-12-2-local_12.2.0-1_amd64.deb
!dpkg -i cuda-repo-ubuntu2004-12-2-local_12.2.0-1_amd64.deb
!apt-key add /var/cuda-repo-ubuntu2004-12-2-local/7fa2af80.pub
!apt-get update
!apt-get -y install cuda

# Setze die Umgebungsvariablen für CUDA
import os
cuda_path = "/usr/local/cuda-12.2/targets/x86_64-linux/lib"
os.environ["PATH"] = "/usr/local/cuda-12.2/bin:" + os.environ.get("PATH", "")
os.environ["LD_LIBRARY_PATH"] = f"{cuda_path}:{os.environ.get('LD_LIBRARY_PATH', '')}"

# Überprüfe, ob libcublas installiert ist
!ls /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcublas.so.12

# Aktualisiere Gradio
!pip install --upgrade gradio

# Starte dein Skript
!python /content/TTS/TTS/demos/xtts_ft_demo/xtts_demo.py

Additional context

No response

[jcgarciaca]

I did !apt install libcublas11 and it worked