Comments (6)
Oh right, the file. train_vits_win.py
.
from thorsten-voice.
I've run into the same problem with "_The process cannot access the file because it is being used by another process" while doing some tests on Windows, but i'm not sure how i solved it. But this happens when training already crashed and the process tries cleaning up the training folder.
- Did you run your command line with admin privilieges?
- Is there any file open from the training directory in explorer?
from thorsten-voice.
The issue I'm having is primarily the RuntimeError: The expanded size of the tensor (1) must match the existing size (2) at non-singleton dimension 0. Target sizes: [1, 44982]. Tensor sizes: [2, 44982]
issue. I don't understand what this is.
(TTS) D:\AI\Testing\TTS>python train_vits.py
> Setting up Audio Processor...
| > sample_rate:44100
| > resample:False
| > num_mels:80
| > log_func:np.log10
| > min_level_db:0
| > frame_shift_ms:None
| > frame_length_ms:None
| > ref_level_db:None
| > fft_size:1024
| > power:None
| > preemphasis:0.0
| > griffin_lim_iters:None
| > signal_norm:None
| > symmetric_norm:None
| > mel_fmin:0
| > mel_fmax:None
| > pitch_fmin:None
| > pitch_fmax:None
| > spec_gain:20.0
| > stft_pad_mode:reflect
| > max_norm:1.0
| > clip_norm:True
| > do_trim_silence:False
| > trim_db:60
| > do_sound_norm:False
| > do_amp_to_db_linear:True
| > do_amp_to_db_mel:True
| > do_rms_norm:False
| > db_level:None
| > stats_path:None
| > base:10
| > hop_length:256
| > win_length:1024
| > Found 15425 files in D:\AI\Testing\TTS\dataset\dataset\LJSpeech-1.1
> Training Environment:
| > Backend: Torch
| > Mixed precision: False
| > Precision: float32
| > Current device: 0
| > Num. of GPUs: 1
| > Num. of CPUs: 12
| > Num. of Torch Threads: 6
| > Torch seed: 54321
| > Torch CUDNN: True
| > Torch CUDNN deterministic: False
| > Torch CUDNN benchmark: False
| > Torch TF32 MatMul: False
> Start Tensorboard: tensorboard --logdir=D:\AI\Testing\TTS\vits_premier1-April-24-2024_07+11PM-dbf1a08a
> Model has 83059180 parameters
> EPOCH: 0/1000
--> D:\AI\Testing\TTS\vits_premier1-April-24-2024_07+11PM-dbf1a08a
> DataLoader initialization
| > Tokenizer:
| > add_blank: True
| > use_eos_bos: False
| > use_phonemes: True
| > phonemizer:
| > phoneme language: en-us
| > phoneme backend: espeak
| > Number of instances : 15271
| > Preprocessing samples
| > Max text length: 200
| > Min text length: 2
| > Avg text length: 82.88874336978587
|
| > Max audio length: 668115
| > Min audio length: 42336
| > Avg audio length: 217587.1818479471
| > Num. instances discarded samples: 0
| > Batch group size: 20.
> TRAINING (2024-04-24 19:13:15)
Traceback (most recent call last):
File "D:\anaconda3\envs\TTS\lib\site-packages\trainer\trainer.py", line 1833, in fit
self._fit()
File "D:\anaconda3\envs\TTS\lib\site-packages\trainer\trainer.py", line 1785, in _fit
self.train_epoch()
File "D:\anaconda3\envs\TTS\lib\site-packages\trainer\trainer.py", line 1503, in train_epoch
for cur_step, batch in enumerate(self.train_loader):
File "D:\anaconda3\envs\TTS\lib\site-packages\torch\utils\data\dataloader.py", line 631, in __next__
data = self._next_data()
File "D:\anaconda3\envs\TTS\lib\site-packages\torch\utils\data\dataloader.py", line 1346, in _next_data
return self._process_data(data)
File "D:\anaconda3\envs\TTS\lib\site-packages\torch\utils\data\dataloader.py", line 1372, in _process_data
data.reraise()
File "D:\anaconda3\envs\TTS\lib\site-packages\torch\_utils.py", line 722, in reraise
raise exception
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "D:\anaconda3\envs\TTS\lib\site-packages\torch\utils\data\_utils\worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "D:\anaconda3\envs\TTS\lib\site-packages\torch\utils\data\_utils\fetch.py", line 54, in fetch
return self.collate_fn(data)
File "D:\AI\Testing\TTS\TTS\tts\models\vits.py", line 343, in collate_fn
wav_padded[i, :, : wav.size(1)] = torch.FloatTensor(wav)
RuntimeError: The expanded size of the tensor (1) must match the existing size (2) at non-singleton dimension 0. Target sizes: [1, 44982]. Tensor sizes: [2, 44982]
Running with administrator privileges results in the same error.
from thorsten-voice.
Sorry for late response. Anything new here or still same error?
from thorsten-voice.
I close this issue, but feel free to reopen it at any time if needed.
from thorsten-voice.
Still same.
from thorsten-voice.
Related Issues (20)
- training duration / female voice? HOT 2
- Request for an oobabooga extension HOT 2
- TTS-Models: Download-Links broken? HOT 2
- Made with Thorsten-Voice 😊 HOT 2
- Windows: tts_to_file ignoring German Umlauts HOT 5
- Request - "synthesize_csv.py" from YouTube "Coqui TTS Audio samples of all models (Version 0.7.1)" HOT 4
- Voz Português Brazil HOT 1
- Emphasis on syllables – How to choose? HOT 7
- Voice synthesizing fails after finetuning HOT 2
- Das Wort "Prolog" führt zu Decoder stopped with `max_decoder_steps` HOT 2
- Issue installing requirements.txt - No matching distribution found for piper-phonemize~=1.1.0 HOT 3
- IPv6 issue HOT 2
- tts gibt nach der Installation nur Ungültiger Maschinenbefehl aus HOT 14
- How to make coqui thorsten voice "more fluent" HOT 2
- GlowTTs HOT 2
- wird es eine app für android auf fdroid geben? HOT 3
- Errors training with newer python HOT 3
- juristische Gesetzesangaben HOT 4
- How to properly read english words in german sentences? HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from thorsten-voice.