trained model

.gitattributes

@@ -25,3 +25,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint_50000.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint_60000.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint_70000.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint_30000.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint_40000.pth filter=lfs diff=lfs merge=lfs -text
+best_model.pth filter=lfs diff=lfs merge=lfs -text
+best_model_45161.pth filter=lfs diff=lfs merge=lfs -text

best_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b41eeba6ae801c324f3f22c3b0ab22a39257c01cd1b09e0eb4080ce66c5c3e35
+size 1041326717

best_model_45161.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b41eeba6ae801c324f3f22c3b0ab22a39257c01cd1b09e0eb4080ce66c5c3e35
+size 1041326717

checkpoint_30000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a286491197e632ed4c5c31679876fe8384be92de292f0d24ac44cb8850ed1e7
+size 1041326589

checkpoint_40000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:903b2b7ec050864623cc17655dad2f44fac81e99b8a754ba7b58a399c6b05f1d
+size 1041326589

checkpoint_50000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e33bbf0a92873ebcf5015032f653967d4e7e6f410d36e5296f104c82e5f903
+size 1041326717

checkpoint_60000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ffd8643368831c58d1ac049679a74db875bcaf3fd7db777cc7f79b1cbc504a
+size 1041326717

checkpoint_70000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11419ab1b75ebdeb7bad74b432cede9ec0b5f6500515df6b9b2de52321f8961a
+size 1041328637

config.json

@@ -0,0 +1,265 @@
+{
+    "output_path": "/run/media/opensuse/Barracuda/Models/TTS_new/trained_common_voice",
+    "logger_uri": null,
+    "run_name": "vits_vctk",
+    "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": 10000,
+    "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": -1,
+    "run_eval": true,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": true,
+    "epochs": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 16,
+    "grad_clip": [
+        1000.0,
+        1000.0
+    ],
+    "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": "",
+    "lr_scheduler_params": {},
+    "use_grad_scaler": false,
+    "cudnn_enable": true,
+    "cudnn_benchmark": true,
+    "torch_seed": 54321,
+    "model": "vits",
+    "num_loader_workers": 4,
+    "num_eval_loader_workers": 4,
+    "use_noise_augment": false,
+    "use_language_weighted_sampler": 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": true,
+        "preemphasis": 0.0,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "log_func": "np.log",
+        "do_trim_silence": true,
+        "trim_db": 23,
+        "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": 1,
+        "do_amp_to_db_linear": false,
+        "do_amp_to_db_mel": true,
+        "pitch_fmax": 640.0,
+        "pitch_fmin": 0.0,
+        "signal_norm": false,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": null
+    },
+    "use_phonemes": false,
+    "phonemizer": null,
+    "phoneme_language": null,
+    "compute_input_seq_cache": true,
+    "text_cleaner": "english_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/run/media/opensuse/Barracuda/Models/TTS_new/trained_common_voice/phoneme_cache",
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.Graphemes",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz",
+        "punctuations": "!'(),-.:;? ",
+        "phonemes": null,
+        "is_unique": false,
+        "is_sorted": true
+    },
+    "add_blank": true,
+    "batch_group_size": 5,
+    "loss_masking": null,
+    "sort_by_audio_len": false,
+    "min_audio_len": 1,
+    "max_audio_len": Infinity,
+    "min_text_len": 1,
+    "max_text_len": 325,
+    "compute_f0": false,
+    "compute_linear_spec": true,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "datasets": [
+        {
+            "name": "vctk",
+            "path": "/run/media/opensuse/Barracuda/Datasets/CommonVoiceMozillaIta/cv-corpus-9.0-2022-04-27/it",
+            "meta_file_train": "",
+            "ignored_speakers": null,
+            "language": "it-it",
+            "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,
+    "model_args": {
+        "num_chars": 67,
+        "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": 6,
+        "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": "1",
+        "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
+        ],
+        "use_sdp": true,
+        "noise_scale": 1.0,
+        "inference_noise_scale": 0.667,
+        "length_scale": 1.0,
+        "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": true,
+        "num_speakers": 1174,
+        "speakers_file": "/run/media/opensuse/Barracuda/Models/TTS_new/trained_common_voice/vits_vctk-June-05-2022_03+45PM-0cf3265a/speakers.json",
+        "d_vector_file": null,
+        "speaker_embedding_channels": 256,
+        "use_d_vector_file": false,
+        "d_vector_dim": 0,
+        "detach_dp_input": true,
+        "use_language_embedding": false,
+        "embedded_language_dim": 4,
+        "num_languages": 0,
+        "language_ids_file": null,
+        "use_speaker_encoder_as_loss": false,
+        "speaker_encoder_config_path": "",
+        "speaker_encoder_model_path": "",
+        "condition_dp_on_speaker": true,
+        "freeze_encoder": false,
+        "freeze_DP": false,
+        "freeze_PE": false,
+        "freeze_flow_decoder": false,
+        "freeze_waveform_decoder": 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": 1.0,
+    "return_wav": true,
+    "r": 1,
+    "num_speakers": 0,
+    "use_speaker_embedding": true,
+    "speakers_file": "/run/media/opensuse/Barracuda/Models/TTS_new/trained_common_voice/vits_vctk-June-05-2022_03+45PM-0cf3265a/speakers.json",
+    "speaker_embedding_channels": 256,
+    "language_ids_file": null,
+    "use_language_embedding": false,
+    "use_d_vector_file": false,
+    "d_vector_file": null,
+    "d_vector_dim": 0
+}

events.out.tfevents.1654436713.localhost.localdomain

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e92fd5923439c12dd6bca13bf200ff0563abc501ab6c6e149ec0d42197a2eb4
+size 34169856

events.out.tfevents.1654765423.localhost.localdomain

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21bab98923e9d5118b49b4b6a40667fb96fe241f40a561bb0da22e9178fa68d3
+size 30282744

info_run.txt

@@ -0,0 +1,7 @@
+sha commit coquitts: 0cf3265a4686d7e856bd472cdaf1572d61cab2b8
+
+PYTORCH_CUDA_ALLOC_CONF="max_split_size_mb:25" CUDA_VISIBLE_DEVICES=1 python recipes/common_voice/vits/train_vits.py
+
+CUDA_VISIBLE_DEVICES=0 tts-server --model_path "/run/media/opensuse/Barracuda/Models/TTS_new/trained_common_voice/vits_vctk-June-05-2022_03+45PM-0cf3265a/best_model.pth" --config_path "/run/media/opensuse/Barracuda/Models/TTS_new/trained_common_voice/vits_vctk-June-05-2022_03+45PM-0cf3265a/config.json"
+
+

train_vits.py

@@ -0,0 +1,139 @@
+import os
+
+from trainer import Trainer, TrainerArgs
+
+from TTS.config.shared_configs import BaseAudioConfig
+from TTS.tts.configs.shared_configs import BaseDatasetConfig
+from TTS.tts.configs.vits_config import VitsConfig
+from TTS.tts.datasets import load_tts_samples
+from TTS.tts.models.vits import Vits, VitsArgs
+from TTS.tts.utils.speakers import SpeakerManager
+from TTS.tts.utils.text.tokenizer import TTSTokenizer
+from TTS.utils.audio import AudioProcessor
+
+# to read tsv files from common voice
+import pandas as pd
+
+# output_path = '/media/popos/Barracuda/Models/TTS_new/trained_common_voice'
+# dataset_path = "/media/popos/Barracuda/Datasets/CommonVoiceMozillaIta/it_29-03-2021/cv-corpus-6.1-2020-12-11/it"
+output_path = '/run/media/opensuse/Barracuda/Models/TTS_new/trained_common_voice'
+dataset_path = "/run/media/opensuse/Barracuda/Datasets/CommonVoiceMozillaIta/cv-corpus-9.0-2022-04-27/it"
+
+pretrained_path = '/run/media/opensuse/Barracuda/Models/TTS_new/trained_common_voice/vits_vctk-June-05-2022_03+45PM-0cf3265a/'
+
+dataset_config = BaseDatasetConfig(
+    name="vctk", meta_file_train="", language="it-it", path=dataset_path
+)
+
+# custom formatter implementation
+
+
+def commonvoice_formatter(root_path, manifest_file, **kwargs):
+    # from root path we have train.tsv, test.tsv and val.tsv or use validated.tsv that contains all
+    txt_file = os.path.join(root_path, 'train.tsv')
+    df = pd.read_csv(txt_file, sep='\t')
+    items = []
+    for i, data in df.iterrows():
+        items.append({
+            "text": data['sentence'],
+            "audio_file": os.path.join(root_path, 'clips', data['path']),
+            "speaker_name": data['client_id']
+        })
+    return items
+
+
+audio_config = BaseAudioConfig(
+    sample_rate=22050,
+    win_length=1024,
+    hop_length=256,
+    num_mels=80,
+    preemphasis=0.0,
+    ref_level_db=20,
+    log_func="np.log",
+    do_trim_silence=True,
+    trim_db=23.0,
+    mel_fmin=0,
+    mel_fmax=None,
+    spec_gain=1.0,
+    signal_norm=False,
+    do_amp_to_db_linear=False,
+    resample=True,
+)
+
+vitsArgs = VitsArgs(
+    use_speaker_embedding=True,
+)
+
+config = VitsConfig(
+    model_args=vitsArgs,
+    audio=audio_config,
+    run_name="vits_vctk",
+    batch_size=32,
+    eval_batch_size=16,
+    batch_group_size=5,
+    num_loader_workers=4,
+    num_eval_loader_workers=4,
+    run_eval=True,
+    test_delay_epochs=-1,
+    epochs=1000,
+    text_cleaner="english_cleaners",
+    use_phonemes=False,
+    phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
+    compute_input_seq_cache=True,
+    print_step=25,
+    print_eval=False,
+    mixed_precision=True,
+    max_text_len=325,  # change this if you have a larger VRAM than 16GB
+    output_path=output_path,
+    datasets=[dataset_config],
+)
+
+# INITIALIZE THE AUDIO PROCESSOR
+# Audio processor is used for feature extraction and audio I/O.
+# It mainly serves to the dataloader and the training loggers.
+ap = AudioProcessor.init_from_config(config)
+
+# INITIALIZE THE TOKENIZER
+# Tokenizer is used to convert text to sequences of token IDs.
+# config is updated with the default characters if not defined in the config.
+tokenizer, config = TTSTokenizer.init_from_config(config)
+
+# LOAD DATA SAMPLES
+# Each sample is a list of ```[text, audio_file_path, speaker_name]```
+# You can define your custom sample loader returning the list of samples.
+# Or define your custom formatter and pass it to the `load_tts_samples`.
+# Check `TTS.tts.datasets.load_tts_samples` for more details.
+train_samples, eval_samples = load_tts_samples(
+    dataset_config, eval_split=True, formatter=commonvoice_formatter)
+
+# init speaker manager for multi-speaker training
+# it maps speaker-id to speaker-name in the model and data-loader
+speaker_manager = SpeakerManager()
+speaker_manager.set_speaker_ids_from_data(train_samples + eval_samples)
+config.model_args.num_speakers = speaker_manager.num_speakers
+
+# init model
+model = Vits(config, ap, tokenizer, speaker_manager)
+
+# init the trainer and 🚀
+if pretrained_path:
+    trainer = Trainer(
+        TrainerArgs(
+            continue_path=pretrained_path,
+        ),
+        config,
+        output_path,
+        model=model,
+        train_samples=train_samples,
+        eval_samples=eval_samples,
+    )
+else:
+    trainer = Trainer(
+        TrainerArgs(),
+        config,
+        output_path,
+        model=model,
+        train_samples=train_samples,
+        eval_samples=eval_samples,
+    )
+trainer.fit()