Error on Training: get_git_branch

[shu-toz]

Hey All,

My Config: 3080 Laptop CUDA 11.8 NVIDIA Driver 552 Windows 11

I tried a lot of different things, fresh install, fresh clone, no dice... Any ideas??

Getting an error when pressing the training button:

tts --model_name tts_models/multilingual/multi-dataset/xtts_v2 --text "Hello World, This is a voice clone speaking." --speaker_wav /workspace/dataset/.wav --language_idx en --use_cuda true>> DVAE weights restored from: C:\xtts-finetune-webui\base_models\v2.0.2\dvae.pth | > Found 17 files in C:\xtts-finetune-webui\finetune_models\dataset Traceback (most recent call last): File "C:\xtts-finetune-webui\xtts_demo.py", line 358, in train_model speaker_xtts_path,config_path, original_xtts_checkpoint, vocab_file, exp_path, speaker_wav = train_gpt(custom_model,version,language, num_epochs, batch_size, grad_acumm, train_csv, eval_csv, output_path=output_path, max_audio_length=max_audio_length) File "C:\xtts-finetune-webui\utils\gpt_train.py", line 184, in train_gpt trainer = Trainer( File "C:\xtts-finetune-webui.venv\lib\site-packages\trainer\trainer.py", line 400, in init config, new_fields = self.init_training(args, coqpit_overrides, config) File "C:\xtts-finetune-webui.venv\lib\site-packages\trainer\trainer.py", line 752, in init_training new_fields["github_branch"] = get_git_branch() File "C:\xtts-finetune-webui.venv\lib\site-packages\trainer\generic_utils.py", line 44, in get_git_branch current = next(line for line in out.split("\n") if line.startswith("")) StopIteration Traceback (most recent call last): File "C:\xtts-finetune-webui.venv\lib\site-packages\gradio\queueing.py", line 459, in call_prediction output = await route_utils.call_process_api( File "C:\xtts-finetune-webui.venv\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api output = await app.get_blocks().process_api( File "C:\xtts-finetune-webui.venv\lib\site-packages\gradio\blocks.py", line 1542, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "C:\xtts-finetune-webui.venv\lib\site-packages\gradio\blocks.py", line 1369, in postprocess_data self.validate_outputs(fn_index, predictions) # type: ignore File "C:\xtts-finetune-webui.venv\lib\site-packages\gradio\blocks.py", line 1343, in validate_outputs raise ValueError( ValueError: An event handler (train_model) didn't receive enough output values (needed: 6, received: 5). Wanted outputs: [label, textbox, textbox, textbox, textbox, textbox] Received outputs: ["The training was interrupted due an error !! Please check the console to check the full error message! Error summary: Traceback (most recent call last): File "C:\xtts-finetune-webui\xtts_demo.py", line 358, in train_model speaker_xtts_path,config_path, original_xtts_checkpoint, vocab_file, exp_path, speaker_wav = train_gpt(custom_model,version,language, num_epochs, batch_size, grad_acumm, train_csv, eval_csv, output_path=output_path, max_audio_length=max_audio_length) File "C:\xtts-finetune-webui\utils\gpt_train.py", line 184, in train_gpt trainer = Trainer( File "C:\xtts-finetune-webui.venv\lib\site-packages\trainer\trainer.py", line 400, in init config, new_fields = self.init_training(args, coqpit_overrides, config) File "C:\xtts-finetune-webui.venv\lib\site-packages\trainer\trainer.py", line 752, in init_training new_fields["github_branch"] = get_git_branch() File "C:\xtts-finetune-webui.venv\lib\site-packages\trainer\generic_utils.py", line 44, in get_git_branch current = next(line for line in out.split("\n") if line.startswith("")) StopIteration ", "", "", "", ""] Traceback (most recent call last): File "C:\xtts-finetune-webui.venv\lib\site-packages\gradio\queueing.py", line 459, in call_prediction output = await route_utils.call_process_api( File "C:\xtts-finetune-webui.venv\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api output = await app.get_blocks().process_api( File "C:\xtts-finetune-webui.venv\lib\site-packages\gradio\blocks.py", line 1542, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "C:\xtts-finetune-webui.venv\lib\site-packages\gradio\blocks.py", line 1369, in postprocess_data self.validate_outputs(fn_index, predictions) # type: ignore File "C:\xtts-finetune-webui.venv\lib\site-packages\gradio\blocks.py", line 1343, in validate_outputs raise ValueError( ValueError: An event handler (train_model) didn't receive enough output values (needed: 6, received: 5). Wanted outputs: [label, textbox, textbox, textbox, textbox, textbox] Received outputs: ["The training was interrupted due an error !! Please check the console to check the full error message! Error summary: Traceback (most recent call last): File "C:\xtts-finetune-webui\xtts_demo.py", line 358, in train_model speaker_xtts_path,config_path, original_xtts_checkpoint, vocab_file, exp_path, speaker_wav = train_gpt(custom_model,version,language, num_epochs, batch_size, grad_acumm, train_csv, eval_csv, output_path=output_path, max_audio_length=max_audio_length) File "C:\xtts-finetune-webui\utils\gpt_train.py", line 184, in train_gpt trainer = Trainer( File "C:\xtts-finetune-webui.venv\lib\site-packages\trainer\trainer.py", line 400, in init config, new_fields = self.init_training(args, coqpit_overrides, config) File "C:\xtts-finetune-webui.venv\lib\site-packages\trainer\trainer.py", line 752, in init_training new_fields["github_branch"] = get_git_branch() File "C:\xtts-finetune-webui.venv\lib\site-packages\trainer\generic_utils.py", line 44, in get_git_branch current = next(line for line in out.split("\n") if line.startswith("")) StopIteration ", "", "", "", ""] The above exception was the direct cause of the following exception: Traceback (most recent call last): File "C:\xtts-finetune-webui.venv\lib\site-packages\gradio\queueing.py", line 497, in process_events response = await self.call_prediction(awake_events, batch) File "C:\xtts-finetune-webui.venv\lib\site-packages\gradio\queueing.py", line 468, in call_prediction raise Exception(str(error) if show_error else None) from error Exception: None

[shu-toz]

Deleted the downloaded models and did everything from scratch, It seemed to have been using the existing XTTS model, which was causing issues.