unable to generate anything

[gucio321]

Command: tts --text "Czesc, jestem syntezator mowy" --model_name "tts_models/pl/mai_female/vits" --vocoder_name "vocoder_models/universal/libri-tts/wavegrad" --out_path /output/

Enviroument:
I have too new python so I use docker. Here is my dockerfile:

Dockerfile

FROM python:3.7

RUN python3 -m pip install TTS

# run bash
CMD ["/bin/bash"]

output:

console output

 > tts_models/pl/mai_female/vits is already downloaded.
 > vocoder_models/universal/libri-tts/wavegrad is already downloaded.
 > Using model: vits
 > Setting up Audio Processor...
 | > sample_rate:22050
 | > 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
 > initialization of speaker-embedding layers.
 > initialization of language-embedding layers.
 > Vocoder Model: wavegrad
 > Text: Czesc, jestem syntezator mowy
 > Text splitted to sentences.
['Czesc, jestem syntezator mowy']
Traceback (most recent call last):
  File "/usr/local/bin/tts", line 8, in <module>
    sys.exit(main())
  File "/usr/local/lib/python3.7/site-packages/TTS/bin/synthesize.py", line 439, in main
    reference_speaker_name=args.reference_speaker_idx,
  File "/usr/local/lib/python3.7/site-packages/TTS/utils/synthesizer.py", line 393, in tts
    vocoder_input = self.vocoder_ap.normalize(mel_postnet_spec.T)
  File "/usr/local/lib/python3.7/site-packages/TTS/utils/audio/processor.py", line 286, in normalize
    raise RuntimeError(" [!] Mean-Var stats does not match the given feature dimensions.")
RuntimeError:  [!] Mean-Var stats does not match the given feature dimensions.
root@1affd8f1442e:/# 

nvidia-smi output

Fri Jul 26 19:51:50 2024       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.90.07              Driver Version: 550.90.07      CUDA Version: 12.4     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA GeForce RTX 2080 ...    Off |   00000000:01:00.0  On |                  N/A |
| N/A   51C    P8              2W /   80W |     718MiB /   8192MiB |     10%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
                                                                                         
+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|    0   N/A  N/A      2959      G   /usr/bin/gnome-shell                          372MiB |
|    0   N/A  N/A      3236    C+G   /usr/bin/xwaylandvideobridge                   13MiB |
|    0   N/A  N/A      3548      G   /usr/bin/Xwayland                              11MiB |
|    0   N/A  N/A      3787      G   /usr/libexec/xdg-desktop-portal-gnome          51MiB |
|    0   N/A  N/A      4010    C+G   /usr/libexec/mutter-x11-frames                 10MiB |
|    0   N/A  N/A     13250      G   /usr/bin/gnome-clocks                          35MiB |
|    0   N/A  N/A     19016      G   ...ures=SpareRendererForSitePerProcess        130MiB |
|    0   N/A  N/A     20426      G   /usr/bin/evolution                              2MiB |
|    0   N/A  N/A     24450      G   ...bin/plasma-browser-integration-host          2MiB |
|    0   N/A  N/A     26279      G   /usr/libexec/kactivitymanagerd                  2MiB |
+-----------------------------------------------------------------------------------------+

I followed instructions from readme. Am I missing something?

[Richdark]

Hi, have you ever found what the issue was? I seem to have the same problem.

[gucio321]

Nope, i think this project is dead or something(?) i just abendoned my idea as it wasn't really important for me tbh.

[Richdark]

True, I haven't even noticed that the last commit is almost 4 years old now. I'm looking at it just for my hobby project though, so it doesn't bother me that much.

Anyway, I found that leaving out --vocoder_name argument completely fixes the issue. Maybe this helps somebody in the future. Thank you for the quick response.