Help in the second stage

[fontnet1]

I started the tutorial with this command
python train.py
What should I do now? I have these files in the picture

According to what is on the site, you should type this command, right?
python train.py --continue_path path/to/previous/run/folder/
But I get an error
This is the error

(FONT2_Vnve) PS C:\ps VsCode\coqui-ai-TTS\data> python train_glowtts.py --continue_path "C:\ps VsCode\coqui-ai-TTS\data\run-January-09-2025_07+26AM-3327b470"

Setting up Audio Processor...
| > sample_rate:22050
| > resample:False
| > num_mels:80
| > log_func:np.log10
| > min_level_db:-100
| > frame_shift_ms:None
| > frame_length_ms:None
| > ref_level_db:20
| > fft_size:1024
| > power:1.5
| > preemphasis:0.0
| > griffin_lim_iters:60
| > signal_norm:True
| > symmetric_norm:True
| > mel_fmin:0
| > mel_fmax:None
| > pitch_fmin:1.0
| > pitch_fmax:640.0
| > spec_gain:20.0
| > stft_pad_mode:reflect
| > max_norm:4.0
| > clip_norm:True
| > do_trim_silence:True
| > trim_db:45
| > 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 13100 files in C:\ps VsCode\coqui-ai-TTS\data\LJSpeech-1.1
Traceback (most recent call last):
File "C:\ps VsCode\coqui-ai-TTS\data\train_glowtts.py", line 79, in
trainer = Trainer(
^^^^^^^^
File "C:\ps VsCode\FONT2_Vnve\Lib\site-packages\trainer\trainer.py", line 190, in init
config, new_fields = self.init_training(args, coqpit_overrides, config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ps VsCode\FONT2_Vnve\Lib\site-packages\trainer\trainer.py", line 527, in init_training
args.restore_path, best_model = get_last_checkpoint(args.continue_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ps VsCode\FONT2_Vnve\Lib\site-packages\trainer\io.py", line 308, in get_last_checkpoint
raise ValueError(msg)
ValueError: No models found in continue path C:\ps VsCode\coqui-ai-TTS\data\run-January-09-2025_07+26AM-3327b470!
(FONT2_Vnve) PS C:\ps VsCode\coqui-ai-TTS\data>

[eginhard]

What are the contents of C:\ps VsCode\coqui-ai-TTS\data\run-January-09-2025_07+26AM-3327b470? Probably you haven't trained the model long enough yet that a checkpoint (*.pth) would be saved. By default, the model is saved only every 10k steps. You can set a lower value for save_step in your GlowTTSConfig.

[fontnet1]

thank you

[fontnet1]

I trained the model but it doesn't work.

Sound creation code
import os
import torch
import json
from TTS.tts.models.glow_tts import GlowTTS
from TTS.tts.configs.glow_tts_config import GlowTTSConfig
from TTS.utils.audio import AudioProcessor
from IPython.display import Audio

مسیرهای ثابت مدل و فایل تنظیمات

model_path = "/content/sample_data/coqui-ai-TTS/data/run-January-11-2025_04+17PM-88485d9e/best_model.pth"
config_path = "/content/sample_data/coqui-ai-TTS/data/run-January-11-2025_04+17PM-88485d9e/config.json"
output_wav_path = "/content/output.wav"

بارگذاری تنظیمات از فایل JSON

with open(config_path, "r") as f:
config_data = json.load(f)

ایجاد شیء پیکربندی

config = GlowTTSConfig(**config_data)

ایجاد پردازشگر صوتی

ap = AudioProcessor.init_from_config(config)

ایجاد مدل

model = GlowTTS(config, ap, tokenizer=None, speaker_manager=None)

بارگذاری وزن‌های مدل

model.load_state_dict(torch.load(model_path, map_location=torch.device("cpu"))["model"])
model.eval() # حالت ارزیابی

متن ورودی

text = "Hello, this is a simple text-to-speech example."

تبدیل متن به توکن‌ها

inputs = model.text_to_sequence(text)

تولید صوت

with torch.no_grad():
outputs = model.infer(inputs)
wav = ap.denormalize(outputs["wav"].squeeze().cpu().numpy())

ذخیره فایل صوتی

ap.save_wav(wav, output_wav_path)

پخش صوت تولید شده

Audio(output_wav_path)

TypeError Traceback (most recent call last)
in <cell line: 19>()
17
18 # ایجاد شیء پیکربندی
---> 19 config = GlowTTSConfig(**config_data)
20
21 # ایجاد پردازشگر صوتی

TypeError: GlowTTSConfig.init() got an unexpected keyword argument 'restore_path'

config.json
{
"output_path": "/content/sample_data/coqui-ai-TTS/data",
"logger_uri": null,
"run_name": "run",
"project_name": null,
"run_description": "\ud83d\udc38Coqui trainer run.",
"print_step": 10,
"plot_step": 100,
"model_param_stats": false,
"wandb_entity": null,
"dashboard_logger": "tensorboard",
"save_on_interrupt": true,
"log_model_step": null,
"save_step": 10000,
"save_n_checkpoints": 5,
"save_checkpoints": true,
"save_all_best": false,
"save_best_after": 0,
"target_loss": null,
"print_eval": false,
"test_delay_epochs": -1,
"run_eval": true,
"run_eval_steps": null,
"distributed_backend": "nccl",
"distributed_url": "tcp://localhost:54321",
"mixed_precision": true,
"precision": "fp16",
"epochs": 2,
"batch_size": 8,
"eval_batch_size": 4,
"grad_clip": 5.0,
"scheduler_after_epoch": true,
"lr": 0.001,
"optimizer": "RAdam",
"optimizer_params": {
"betas": [
0.9,
0.998
],
"weight_decay": 1e-06
},
"lr_scheduler": "NoamLR",
"lr_scheduler_params": {
"warmup_steps": 4000
},
"use_grad_scaler": false,
"allow_tf32": false,
"cudnn_enable": true,
"cudnn_deterministic": false,
"cudnn_benchmark": false,
"training_seed": 54321,
"model": "glow_tts",
"num_loader_workers": 2,
"num_eval_loader_workers": 2,
"use_noise_augment": false,
"audio": {
"fft_size": 1024,
"win_length": 1024,
"hop_length": 256,
"frame_shift_ms": null,
"frame_length_ms": null,
"stft_pad_mode": "reflect",
"sample_rate": 22050,
"resample": false,
"preemphasis": 0.0,
"ref_level_db": 20,
"do_sound_norm": false,
"log_func": "np.log10",
"do_trim_silence": true,
"trim_db": 45,
"do_rms_norm": false,
"db_level": null,
"power": 1.5,
"griffin_lim_iters": 60,
"num_mels": 80,
"mel_fmin": 0.0,
"mel_fmax": null,
"spec_gain": 20,
"do_amp_to_db_linear": true,
"do_amp_to_db_mel": true,
"pitch_fmax": 640.0,
"pitch_fmin": 1.0,
"signal_norm": true,
"min_level_db": -100,
"symmetric_norm": true,
"max_norm": 4.0,
"clip_norm": true,
"stats_path": null
},
"use_phonemes": true,
"phonemizer": "gruut",
"phoneme_language": "en-us",
"compute_input_seq_cache": false,
"text_cleaner": "phoneme_cleaners",
"enable_eos_bos_chars": false,
"test_sentences_file": "",
"phoneme_cache_path": "/content/sample_data/coqui-ai-TTS/data/phoneme_cache",
"characters": {
"characters_class": "TTS.tts.utils.text.characters.IPAPhonemes",
"vocab_dict": null,
"pad": "",
"eos": "",
"bos": "",
"blank": "",
"characters": "iy\u0268\u0289\u026fu\u026a\u028f\u028ae\u00f8\u0258\u0259\u0275\u0264o\u025b\u0153\u025c\u025e\u028c\u0254\u00e6\u0250a\u0276\u0251\u0252\u1d7b\u0298\u0253\u01c0\u0257\u01c3\u0284\u01c2\u0260\u01c1\u029bpbtd\u0288\u0256c\u025fk\u0261q\u0262\u0294\u0274\u014b\u0272\u0273n\u0271m\u0299r\u0280\u2c71\u027e\u027d\u0278\u03b2fv\u03b8\u00f0sz\u0283\u0292\u0282\u0290\u00e7\u029dx\u0263\u03c7\u0281\u0127\u0295h\u0266\u026c\u026e\u028b\u0279\u027bj\u0270l\u026d\u028e\u029f\u02c8\u02cc\u02d0\u02d1\u028dw\u0265\u029c\u02a2\u02a1\u0255\u0291\u027a\u0267\u02b2\u0303\u025a\u02de\u026b",
"punctuations": "!'(),-.:;? ",
"phonemes": null,
"is_unique": false,
"is_sorted": true
},
"add_blank": false,
"batch_group_size": 0,
"loss_masking": null,
"min_audio_len": 1,
"max_audio_len": Infinity,
"min_text_len": 1,
"max_text_len": Infinity,
"compute_f0": false,
"compute_energy": false,
"compute_linear_spec": false,
"precompute_num_workers": 0,
"start_by_longest": false,
"shuffle": false,
"drop_last": false,
"datasets": [
{
"formatter": "ljspeech",
"dataset_name": "",
"path": "/content/sample_data/coqui-ai-TTS/data/recipes/ljspeech/LJSpeech-1.1/",
"meta_file_train": "metadata.csv",
"ignored_speakers": null,
"language": "",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
}
],
"test_sentences": [
"It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
"Be a voice, not an echo.",
"I'm sorry Dave. I'm afraid I can't do that.",
"This cake is great. It's so delicious and moist.",
"Prior to November 22, 1963."
],
"eval_split_max_size": null,
"eval_split_size": 0.01,
"use_speaker_weighted_sampler": false,
"speaker_weighted_sampler_alpha": 1.0,
"use_language_weighted_sampler": false,
"language_weighted_sampler_alpha": 1.0,
"use_length_weighted_sampler": false,
"length_weighted_sampler_alpha": 1.0,
"num_chars": 132,
"encoder_type": "rel_pos_transformer",
"encoder_params": {
"kernel_size": 3,
"dropout_p": 0.1,
"num_layers": 6,
"num_heads": 2,
"hidden_channels_ffn": 768,
"input_length": null
},
"use_encoder_prenet": true,
"hidden_channels_enc": 192,
"hidden_channels_dec": 192,
"hidden_channels_dp": 256,
"dropout_p_dp": 0.1,
"dropout_p_dec": 0.05,
"mean_only": true,
"out_channels": 80,
"num_flow_blocks_dec": 12,
"inference_noise_scale": 0.0,
"kernel_size_dec": 5,
"dilation_rate": 1,
"num_block_layers": 4,
"num_speakers": 0,
"c_in_channels": 0,
"num_splits": 4,
"num_squeeze": 2,
"sigmoid_scale": false,
"d_vector_dim": 0,
"data_dep_init_steps": 10,
"style_wav_for_test": null,
"length_scale": 1.0,
"use_speaker_embedding": false,
"speakers_file": null,
"use_d_vector_file": false,
"d_vector_file": false,
"min_seq_len": 3,
"max_seq_len": 500,
"r": 1,
"restore_path": "/content/sample_data/coqui-ai-TTS/data/run-January-11-2025_03+04PM-88485d9e/best_model.pth",
"github_branch": "* dev"
}

[eginhard]

There is an error message that tells you what the issue is.

[fontnet1]

Hello, look at the arrow again. It's very confusing. Maybe I wrote the sound creation code wrong. Look.

[fontnet1]

I even checked the file path and it was correct.

[eginhard]

Remove the space at the beginning of model_path and config_path. Also, please share code as text and not as images in the future to make it more accessible and easier to read.

[fontnet1]

Thank you, I finally succeeded after a month. Now I have to teach a model for Persian. Thank you. @eginhard