tts / config.json
Sham786's picture
Upload folder using huggingface_hub
92ea733 verified
{
"output_path": "output",
"logger_uri": null,
"run_name": "run",
"project_name": null,
"run_description": "\ud83d\udc38Coqui trainer run.",
"print_step": 25,
"plot_step": 100,
"model_param_stats": false,
"wandb_entity": null,
"dashboard_logger": "tensorboard",
"log_model_step": null,
"save_step": 10000,
"save_n_checkpoints": 5,
"save_checkpoints": true,
"save_all_best": false,
"save_best_after": 10000,
"target_loss": null,
"print_eval": false,
"test_delay_epochs": 0,
"run_eval": true,
"run_eval_steps": null,
"distributed_backend": "nccl",
"distributed_url": "tcp://localhost:54321",
"mixed_precision": false,
"epochs": 1000,
"batch_size": 32,
"eval_batch_size": 16,
"grad_clip": 0.0,
"scheduler_after_epoch": true,
"lr": 0.001,
"optimizer": "radam",
"optimizer_params": null,
"lr_scheduler": null,
"lr_scheduler_params": {},
"use_grad_scaler": false,
"cudnn_enable": true,
"cudnn_deterministic": false,
"cudnn_benchmark": false,
"training_seed": 54321,
"model": "tortoise",
"num_loader_workers": 0,
"num_eval_loader_workers": 0,
"use_noise_augment": false,
"audio": {
"sample_rate": 22050,
"diffusion_sample_rate": 24000,
"output_sample_rate": 24000
},
"use_phonemes": false,
"phonemizer": null,
"phoneme_language": null,
"compute_input_seq_cache": false,
"text_cleaner": null,
"enable_eos_bos_chars": false,
"test_sentences_file": "",
"phoneme_cache_path": null,
"characters": null,
"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": "",
"dataset_name": "",
"path": "",
"meta_file_train": "",
"ignored_speakers": null,
"language": "",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
}
],
"test_sentences": [],
"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,
"model_args": {
"autoregressive_batch_size": 1,
"enable_redaction": false,
"high_vram": false,
"kv_cache": true,
"ar_checkpoint": null,
"clvp_checkpoint": null,
"diff_checkpoint": null,
"num_chars": 255,
"ar_max_mel_tokens": 604,
"ar_max_text_tokens": 402,
"ar_max_conditioning_inputs": 2,
"ar_layers": 30,
"ar_model_dim": 1024,
"ar_heads": 16,
"ar_number_text_tokens": 255,
"ar_start_text_token": 255,
"ar_checkpointing": false,
"ar_train_solo_embeddings": false,
"diff_model_channels": 1024,
"diff_num_layers": 10,
"diff_in_channels": 100,
"diff_out_channels": 200,
"diff_in_latent_channels": 1024,
"diff_in_tokens": 8193,
"diff_dropout": 0,
"diff_use_fp16": false,
"diff_num_heads": 16,
"diff_layer_drop": 0,
"diff_unconditioned_percentage": 0,
"clvp_dim_text": 768,
"clvp_dim_speech": 768,
"clvp_dim_latent": 768,
"clvp_num_text_tokens": 256,
"clvp_text_enc_depth": 20,
"clvp_text_seq_len": 350,
"clvp_text_heads": 12,
"clvp_num_speech_tokens": 8192,
"clvp_speech_enc_depth": 20,
"clvp_speech_heads": 12,
"clvp_speech_seq_len": 430,
"clvp_use_xformers": true,
"duration_const": 102400
},
"model_dir": null,
"temperature": 0.2,
"length_penalty": 1.0,
"repetition_penalty": 2.0,
"top_p": 0.8,
"cond_free_k": 2.0,
"diffusion_temperature": 1.0,
"num_autoregressive_samples": 16,
"diffusion_iterations": 30,
"sampler": "ddim"
}