Hugging Face's logo

formospeech
/
yourtts-htia-240704

Text-to-Speech
Transformers
Hakka Chinese
Inference Endpoints
Model card Files Community
yourtts-htia-240704 / config.json
txya900619's picture
txya900619
upload: model pth and configs
e523ebb
raw
history blame contribute delete
24.2 kB
{
"output_path": "/home/wayne/TTS/recipes/hat-tts/vits/results",
"logger_uri": null,
"run_name": "vits_hat_tts",
"project_name": "vits_hat_tts",
"run_description": "\ud83d\udc38Coqui trainer run.",
"print_step": 100,
"plot_step": 100,
"model_param_stats": false,
"wandb_entity": null,
"dashboard_logger": "wandb",
"save_on_interrupt": true,
"log_model_step": 10000,
"save_step": 10000,
"save_n_checkpoints": 5,
"save_checkpoints": true,
"save_all_best": false,
"save_best_after": 50,
"target_loss": "loss_1",
"print_eval": true,
"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": 500,
"batch_size": 54,
"eval_batch_size": 128,
"grad_clip": [
5.0,
5.0
],
"scheduler_after_epoch": true,
"lr": 0.001,
"optimizer": "AdamW",
"optimizer_params": {
"betas": [
0.8,
0.99
],
"eps": 1e-09,
"weight_decay": 0.01
},
"lr_scheduler": null,
"lr_scheduler_params": {},
"use_grad_scaler": false,
"allow_tf32": false,
"cudnn_enable": true,
"cudnn_deterministic": false,
"cudnn_benchmark": false,
"training_seed": 54321,
"model": "vits",
"num_loader_workers": 16,
"num_eval_loader_workers": 16,
"use_noise_augment": false,
"audio": {
"fft_size": 1024,
"sample_rate": 22050,
"win_length": 1024,
"hop_length": 256,
"num_mels": 80,
"mel_fmin": 0,
"mel_fmax": null
},
"use_phonemes": false,
"phonemizer": null,
"phoneme_language": null,
"compute_input_seq_cache": true,
"text_cleaner": null,
"enable_eos_bos_chars": false,
"test_sentences_file": "",
"phoneme_cache_path": null,
"characters": {
"characters_class": "TTS.tts.models.vits.VitsCharacters",
"vocab_dict": null,
"pad": "_",
"eos": "&",
"bos": "*",
"blank": null,
"characters": [
"11",
"113",
"2",
"21",
"24",
"31",
"33",
"35",
"43",
"5",
"53",
"54",
"55",
"a",
"b",
"d",
"e",
"f",
"h",
"i",
"j",
"k",
"l",
"m",
"n",
"o",
"p",
"s",
"t",
"u",
"v",
"w",
"z",
"~",
"\u00e6",
"\u00f0",
"\u014b",
"\u0251",
"\u0254",
"\u0255",
"\u0259",
"\u025a",
"\u025b",
"\u025d",
"\u0261",
"\u0268",
"\u026a",
"\u0279",
"\u0282",
"\u0283",
"\u0288",
"\u028a",
"\u028c",
"\u0290",
"\u0292",
"\u02b0",
"\u0329",
"\u0361",
"\u03b8"
],
"punctuations": "\uff0c ",
"phonemes": null,
"is_unique": true,
"is_sorted": true
},
"add_blank": true,
"batch_group_size": 2,
"loss_masking": null,
"min_audio_len": 1,
"max_audio_len": 661500,
"min_text_len": 1,
"max_text_len": Infinity,
"compute_f0": false,
"compute_energy": false,
"compute_linear_spec": true,
"precompute_num_workers": 0,
"start_by_longest": false,
"shuffle": false,
"drop_last": false,
"datasets": [
{
"formatter": "hat_tts",
"dataset_name": "hat_tts_sixian",
"path": "/home/wayne/Corpora/hat_tts",
"meta_file_train": "sixian_concat.json",
"ignored_speakers": null,
"language": "sixian",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
},
{
"formatter": "hat_tts",
"dataset_name": "hat_tts_hailu",
"path": "/home/wayne/Corpora/hat_tts",
"meta_file_train": "hailu_concat.json",
"ignored_speakers": null,
"language": "hailu",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
},
{
"formatter": "hakka_tts_general",
"dataset_name": "hac_vocab_dapu_e",
"path": "/home/wayne/Corpora/hac_vocab",
"meta_file_train": "dapu_e_concat.json",
"ignored_speakers": null,
"language": "dapu",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
},
{
"formatter": "hakka_tts_general",
"dataset_name": "hac_vocab_hailu_e",
"path": "/home/wayne/Corpora/hac_vocab",
"meta_file_train": "hailu_e_concat.json",
"ignored_speakers": null,
"language": "hailu",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
},
{
"formatter": "hakka_tts_general",
"dataset_name": "hac_vocab_raoping_e",
"path": "/home/wayne/Corpora/hac_vocab",
"meta_file_train": "raoping_e_concat.json",
"ignored_speakers": null,
"language": "raoping",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
},
{
"formatter": "hakka_tts_general",
"dataset_name": "hac_vocab_sixian_e",
"path": "/home/wayne/Corpora/hac_vocab",
"meta_file_train": "sixian_e_concat.json",
"ignored_speakers": null,
"language": "sixian",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
},
{
"formatter": "hakka_tts_general",
"dataset_name": "hac_vocab_zhaoan_e",
"path": "/home/wayne/Corpora/hac_vocab",
"meta_file_train": "zhaoan_e_concat.json",
"ignored_speakers": null,
"language": "zhaoan",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
},
{
"formatter": "hat_tts",
"dataset_name": "hakkaradio_news_dapu",
"path": "/home/wayne/Corpora/hakkaradio_news",
"meta_file_train": "dapu_concat.json",
"ignored_speakers": null,
"language": "dapu",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
},
{
"formatter": "hat_tts",
"dataset_name": "hakkaradio_news_hailu",
"path": "/home/wayne/Corpora/hakkaradio_news",
"meta_file_train": "hailu_concat.json",
"ignored_speakers": null,
"language": "hailu",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
},
{
"formatter": "hat_tts",
"dataset_name": "hakkaradio_news_raoping",
"path": "/home/wayne/Corpora/hakkaradio_news",
"meta_file_train": "raoping_concat.json",
"ignored_speakers": null,
"language": "raoping",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
},
{
"formatter": "hat_tts",
"dataset_name": "hakkaradio_news_sixian",
"path": "/home/wayne/Corpora/hakkaradio_news",
"meta_file_train": "sixian_concat.json",
"ignored_speakers": null,
"language": "sixian",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
},
{
"formatter": "hat_tts",
"dataset_name": "hakkaradio_news_zhaoan",
"path": "/home/wayne/Corpora/hakkaradio_news",
"meta_file_train": "zhaoan_concat.json",
"ignored_speakers": null,
"language": "zhaoan",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
}
],
"test_sentences": [
[
[
"t",
"\u02b0",
"u",
"\u014b",
"11",
"h",
"o",
"k",
"5"
],
"XF",
null,
"sixian"
],
[
[
"p",
"e",
"t",
"2",
"p",
"\u02b0",
"u",
"55"
],
"XF",
null,
"sixian"
],
[
[
"v",
"u",
"k",
"2",
"h",
"a",
"24"
],
"XF",
null,
"sixian"
],
[
[
"k",
"\u02b0",
"o",
"n",
"55",
"t",
"e",
"t",
"2",
" ",
"t",
"o",
"55"
],
"XF",
null,
"sixian"
],
[
[
"\u014b",
"a",
"24",
"\u0255",
"i",
"n",
"24",
"s",
"a",
"\u014b",
"24",
" ",
"t",
"o",
"31",
"\u0255",
"i",
"n",
"24",
"s",
"a",
"m",
"24",
" ",
"\uff0c",
" ",
"h",
"i",
"55",
" ",
"t",
"\u02b0",
"o",
"i",
"11",
"p",
"e",
"t",
"2",
"s",
"\u0268",
"55",
" ",
"k",
"e",
"55",
" ",
"k",
"u",
"e",
"t",
"2",
"k",
"a",
"24",
" ",
"i",
"m",
"24",
"l",
"o",
"k",
"5",
"t",
"\u02b0",
"a",
"\u014b",
"24",
" ",
"\uff0c",
" ",
"t",
"\u02b0",
"a",
"\u014b",
"24",
"i",
"m",
"24",
"\u014b",
"o",
"k",
"5",
" ",
"f",
"i",
"55"
],
"XF",
null,
"sixian"
],
[
[
"t",
"\u02b0",
"u",
"\u014b",
"55",
"h",
"o",
"k",
"2"
],
"HF",
null,
"hailu"
],
[
[
"p",
"e",
"t",
"5",
"p",
"\u02b0",
"u",
"33"
],
"HF",
null,
"hailu"
],
[
[
"v",
"u",
"k",
"5",
"h",
"a",
"53"
],
"HF",
null,
"hailu"
],
[
[
"k",
"\u02b0",
"o",
"n",
"11",
"t",
"e",
"t",
"5",
" ",
"t",
"o",
"11"
],
"HF",
null,
"hailu"
],
[
[
"n",
"a",
"m",
"55",
"\u014b",
"\u0329",
"24",
" ",
"p",
"\u02b0",
"i",
"n",
"55",
"t",
"e",
"n",
"24",
" ",
"k",
"a",
"i",
"11",
" ",
"\u0282",
"i",
"55",
"t",
"\u02b0",
"o",
"i",
"33",
" ",
"\uff0c",
" ",
"p",
"\u02b0",
"i",
"a",
"\u014b",
"55",
"p",
"\u02b0",
"i",
"a",
"\u014b",
"55",
" ",
"t",
"\u0361",
"s",
"o",
"11",
"t",
"e",
"t",
"5",
" ",
"\u0282",
"i",
"u",
"33",
" ",
"k",
"a",
"u",
"11",
"\u0290",
"u",
"k",
"2"
],
"HF",
null,
"hailu"
],
[
[
"k",
"o",
"53",
" ",
"p",
"\u02b0",
"i",
"e",
"t",
"21",
" ",
"t",
"i",
"a",
"m",
"31",
"\u014b",
"u",
"a",
"i",
"53",
"\u0288",
"\u0282",
"u",
"\u014b",
"33",
" ",
"k",
"i",
"u",
"31",
" ",
"s",
"\u0268",
"33",
" ",
"l",
"o",
"i",
"113",
" ",
"t",
"o",
"53",
" ",
"t",
"\u02b0",
"u",
"\u014b",
"113",
"f",
"a",
"33",
" ",
"l",
"i",
"m",
"113",
" ",
"h",
"a",
"33"
],
"\u5b8b\u6db5\u8473",
null,
"dapu"
],
[
[
"a",
"11",
" ",
"n",
"a",
"i",
"11",
" ",
"\uff0c",
" ",
"\u014b",
"i",
"55",
" ",
"k",
"i",
"a",
"k",
"2",
"k",
"i",
"a",
"k",
"2",
" ",
"l",
"o",
"i",
"55",
" ",
"k",
"\u02b0",
"a",
"n",
"24",
" ",
"s",
"i",
"n",
"11",
"v",
"u",
"n",
"55",
" ",
"p",
"o",
"53",
"t",
"\u02b0",
"o",
"11",
" ",
"\uff0c",
" ",
"s",
"\u0268",
"11",
" ",
"h",
"e",
"24",
" ",
"n",
"i",
"55",
" ",
"\u0288",
"\u0282",
"a",
"n",
"11",
" ",
"v",
"u",
"k",
"2"
],
"\u5468\u78a9\u8208",
null,
"raoping"
],
[
[
"h",
"i",
"e",
"t",
"24",
"\u014b",
"i",
"e",
"t",
"43",
" ",
"k",
"a",
"i",
"31",
" ",
"\u0282",
"i",
"53",
"b",
"u",
"55",
" ",
"\uff0c",
" ",
"a",
"11",
" ",
"t",
"s",
"\u02b0",
"i",
"u",
"\u014b",
"53",
" ",
"k",
"u",
"i",
"11",
" ",
"b",
"u",
"24",
"h",
"a",
"11",
" ",
"\u0288",
"\u0282",
"\u025b",
"n",
"31",
"k",
"\u02b0",
"u",
"i",
"31",
" ",
"t",
"s",
"\u02b0",
"a",
"i",
"55",
" ",
"k",
"\u02b0",
"a",
"24",
" ",
"t",
"s",
"o",
"\u014b",
"11",
" ",
"k",
"a",
"i",
"31",
" ",
"l",
"\u0254",
"31",
"b",
"u",
"24"
],
"\u5ed6\u80b2\u8fb0",
null,
"zhaoan"
]
],
"eval_split_max_size": null,
"eval_split_size": 0.01429,
"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": {
"num_chars": 63,
"out_channels": 513,
"spec_segment_size": 32,
"hidden_channels": 192,
"hidden_channels_ffn_text_encoder": 768,
"num_heads_text_encoder": 2,
"num_layers_text_encoder": 8,
"kernel_size_text_encoder": 3,
"dropout_p_text_encoder": 0.1,
"dropout_p_duration_predictor": 0.5,
"kernel_size_posterior_encoder": 5,
"dilation_rate_posterior_encoder": 1,
"num_layers_posterior_encoder": 16,
"kernel_size_flow": 5,
"dilation_rate_flow": 1,
"num_layers_flow": 4,
"resblock_type_decoder": "2",
"resblock_kernel_sizes_decoder": [
3,
7,
11
],
"resblock_dilation_sizes_decoder": [
[
1,
3,
5
],
[
1,
3,
5
],
[
1,
3,
5
]
],
"upsample_rates_decoder": [
8,
8,
2,
2
],
"upsample_initial_channel_decoder": 512,
"upsample_kernel_sizes_decoder": [
16,
16,
4,
4
],
"periods_multi_period_discriminator": [
2,
3,
5,
7,
11
],
"use_sdp": true,
"noise_scale": 1.0,
"inference_noise_scale": 0.667,
"length_scale": 1,
"noise_scale_dp": 1.0,
"inference_noise_scale_dp": 1.0,
"max_inference_len": null,
"init_discriminator": true,
"use_spectral_norm_disriminator": false,
"use_speaker_embedding": false,
"num_speakers": 0,
"speakers_file": "speakers.pth",
"d_vector_file": [ "speaker_embs.pth" ],
"speaker_embedding_channels": 256,
"use_d_vector_file": true,
"d_vector_dim": 512,
"detach_dp_input": true,
"use_language_embedding": true,
"embedded_language_dim": 4,
"num_languages": 0,
"language_ids_file": "language_ids.json",
"use_speaker_encoder_as_loss": false,
"speaker_encoder_config_path": "https://github.com/coqui-ai/TTS/releases/download/speaker_encoder_model/config_se.json",
"speaker_encoder_model_path": "https://github.com/coqui-ai/TTS/releases/download/speaker_encoder_model/model_se.pth.tar",
"condition_dp_on_speaker": true,
"freeze_encoder": false,
"freeze_DP": false,
"freeze_PE": false,
"freeze_flow_decoder": false,
"freeze_waveform_decoder": false,
"encoder_sample_rate": null,
"interpolate_z": true,
"reinit_DP": false,
"reinit_text_encoder": false
},
"lr_gen": 0.0002,
"lr_disc": 0.0002,
"lr_scheduler_gen": "ExponentialLR",
"lr_scheduler_gen_params": {
"gamma": 0.999875,
"last_epoch": -1
},
"lr_scheduler_disc": "ExponentialLR",
"lr_scheduler_disc_params": {
"gamma": 0.999875,
"last_epoch": -1
},
"kl_loss_alpha": 1.0,
"disc_loss_alpha": 1.0,
"gen_loss_alpha": 1.0,
"feat_loss_alpha": 1.0,
"mel_loss_alpha": 45.0,
"dur_loss_alpha": 1.0,
"speaker_encoder_loss_alpha": 9.0,
"return_wav": true,
"use_weighted_sampler": false,
"weighted_sampler_attrs": {},
"weighted_sampler_multipliers": {},
"r": 1,
"num_speakers": 0,
"use_speaker_embedding": false,
"speakers_file": "speakers.pth",
"speaker_embedding_channels": 256,
"language_ids_file": "language_ids.json",
"use_language_embedding": true,
"use_d_vector_file": true,
"d_vector_file": [ "speaker_embs.pth" ],
"d_vector_dim": 512
}