DrewThomasson
commented
5 months ago Sorry about the late responses I'll look into this, hm
-Ok good so its only the custom model thing,
Mind if you also show me what files were in the model folder you imported?,
Solution?:
It appears that when you imported the custom model folder it may of not had the the config.json file in it
FileNotFoundError: [Errno 2] No such file or directory: 'tortoise/voices/daniel.M/model/config.json'
The (fine tuning xtts model ) Google colab should of given you these files on the final export code, cause these three files are needed for it to work
-config.json -vocab.json -model.pth
*in refrence to the final code block in the (fine tuning xtts model) Google Colab:
!mkdir /content/drive/MyDrive/XTTS_ft_colab shutil.copy(os.path.join(model_dir, 'config.json'), "/content/drive/MyDrive/XTTS_ft_colab/config.json") shutil.copy(os.path.join(model_dir, 'vocab.json'), "/content/drive/MyDrive/XTTS_ft_colab/vocab.json'") shutil.copy('model.pth', "/content/drive/MyDrive/XTTS_ft_colab/model.pth")
If you have them stored somewhere, you can manually make sure that they are in the folder 'tortoise/voices/daniel.M/model/' within the VoxNovel folder on the WSl Ubuntu machine
Hope it Helps!
I am using WLS Ubuntu on windows
Selected TTS model: tts_models/multilingual/multi-dataset/xtts_v1.1 Selected TTS model: tts_models/multilingual/multi-dataset/xtts_v2 Updated voice for 2493:NATO.?: daniel.M Updated voice for Narrator: daniel.M Language for Narrator changed to en Updated voice for Narrator: daniel.M Added voice actor data to Working_files/Book/book.csv Added language data to the CSV file. Voice actor: daniel.M, en found fine tuned for voice actor: daniel.M: loading custom model... Exception in thread Thread-1 (generate_audio): Traceback (most recent call last): File "/home/unix/miniconda3/envs/VoxNovel/lib/python3.10/threading.py", line 1016, in _bootstrap_inner self.run() File "/home/unix/miniconda3/envs/VoxNovel/lib/python3.10/threading.py", line 953, in run self._target(*self._args, **self._kwargs) File "/home/unix/VoxNovel/2GPU_Audio_generation.py", line 1916, in generate_audio fineTune_audio_generate(text=fragment, file_path=f"Working_files/temp/{temp_count}.wav", speaker_wav=speaker_wavz[0], language=language_code, voice_actor=voice_actor) File "/home/unix/VoxNovel/2GPU_Audio_generation.py", line 1746, in fineTune_audio_generate config.load_json(CONFIG_PATH) File "/home/unix/miniconda3/envs/VoxNovel/lib/python3.10/site-packages/coqpit/coqpit.py", line 726, in load_json with open(file_name, "r", encoding="utf8") as f: FileNotFoundError: [Errno 2] No such file or directory: 'tortoise/voices/daniel.M/model/config.json' CSV Index: 0 audio_0_0 Playing Working_files/generated_audio_clips/audio_0_0.wav Could not play the audio file: No file 'Working_files/generated_audio_clips/audio_0_0.wav' found in working directory '/home/unix/VoxNovel'. CSV Index: 1 audio_1_0 Playing Working_files/generated_audio_clips/audio_1_0.wav Could not play the audio file: No file 'Working_files/generated_audio_clips/audio_1_0.wav' found in working directory '/home/unix/VoxNovel'.
/home/unix/miniconda3/envs/VoxNovel/cd /home/unix/miniconda3/envs/VoxNovel/