Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+trainer_0_log.txt filter=lfs diff=lfs merge=lfs -text

best_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631587b496fb613247cf0a78ab354e72863368223f6b82dc84626ad926226adb
+size 1038013606

best_model_108884.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b912efdda67808de64cbdffbf55fa3f9b9d15ad150d31d2595dab5690b680891
+size 1038013478

best_model_175669.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:325ed979647a58962519700420f8e62a9f6d8e016f8ee4abcf07d13ebdc6e4f0
+size 1038013606

best_model_176337.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e39e7609f19c5dde5619beee0c66b7f523e95607a2274e3736dc9660b88fa01
+size 1038013606

best_model_187693.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb89d8378d30f217a30d197cb1299e256a57bb46b171f577b39c56a398d7144e
+size 1038013606

best_model_200386.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8505496a820edfefa45b5f1254b08a06a30d5cbd87a44670f49f12193b854ac7
+size 1038013606

best_model_217086.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631587b496fb613247cf0a78ab354e72863368223f6b82dc84626ad926226adb
+size 1038013606

best_model_80828.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5a9b4af405f8f78df0fde6c42636f5884c0c9a380d77b838e29c6a08cffd78
+size 1038013478

checkpoint_205000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b02808d6e982312fec36e84b39d8889864e88b1e6fca234e4e9f636b339c30
+size 1038013606

checkpoint_210000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af4882c6f0ae03f67d33b063ef235a85e0bc2f51b5064bb9571784a3a1bdcd1
+size 1038013606

checkpoint_215000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c440fcaf142ca861385fb6153ab05cef105b0a252b4a82482b7e4c1ecc307f3
+size 1038013606

checkpoint_220000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c6a85f4d8ea33ce8b94f35f9cc919af646f15e561d79e568aeff5c16f26950a
+size 1038013606

checkpoint_225000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8bafea5973eeead1c73c939e9e5c3cd5b191974c608e85c35f99da296a3b818
+size 1038013606

checkpoint_230000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ff8af83dd799f8f64f7ed6a4f90feef314ca8c8962a744b7815fd75496b3b6b
+size 1038013606

checkpoint_235000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b045afe29d4d7f419ea43874ae58bbedcdaef1291f8ee62b09ac0ae32aae38f2
+size 1038013606

checkpoint_240000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb2da8f4d175c73c531c68f9b49be077e8f998637b76d37893b090dfc3002c1
+size 1038013606

checkpoint_245000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a401cf5b9cc3a46d85fd50462dbbec5d3cb2ec091b3049269bdd58436a366ef
+size 1038013606

checkpoint_250000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eddcc2845982597540565e840578cffc0642ece0b43957f66d088b1dd604e7c0
+size 1038013606

config.json

@@ -0,0 +1,271 @@
+{
+    "output_path": "vits_hausa",
+    "logger_uri": null,
+    "run_name": "vits_openbible_hausa",
+    "project_name": null,
+    "run_description": "vits_openbible_hausa",
+    "print_step": 25,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "save_on_interrupt": true,
+    "log_model_step": 5000,
+    "save_step": 5000,
+    "save_n_checkpoints": 10,
+    "save_checkpoints": true,
+    "save_all_best": true,
+    "save_best_after": 0,
+    "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": 1000,
+    "batch_size": 26,
+    "eval_batch_size": 26,
+    "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": null,
+    "lr_scheduler_params": null,
+    "use_grad_scaler": false,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "vits",
+    "num_loader_workers": 12,
+    "num_eval_loader_workers": 12,
+    "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": "no_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": null,
+    "characters": {
+        "characters_class": "TTS.tts.models.vits.VitsCharacters",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "ABCDEFGHIJKLMNORSTUWYZabcdefghijklmnorstuwyz\u0101\u0103\u016b\u0181\u018a\u0198\u0199\u0253\u0257\u2019",
+        "punctuations": " !',.:;?",
+        "phonemes": null,
+        "is_unique": true,
+        "is_sorted": true
+    },
+    "add_blank": true,
+    "batch_group_size": 5,
+    "loss_masking": null,
+    "min_audio_len": 1,
+    "max_audio_len": 264600,
+    "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": true,
+    "shuffle": false,
+    "drop_last": false,
+    "datasets": [
+        {
+            "formatter": "",
+            "dataset_name": "",
+            "path": "data",
+            "meta_file_train": "manifest_train.jsonl",
+            "ignored_speakers": null,
+            "language": "ha",
+            "phonemizer": "",
+            "meta_file_val": "manifest_dev.jsonl",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "Umarnai don zaman tsarki",
+            "two",
+            null,
+            "ha"
+        ],
+        [
+            "wanda kuma ya fa\u0257a mana \u0199aunar da kuke yi cikin Ruhu.",
+            "one",
+            null,
+            "ha"
+        ],
+        [
+            "Gama mun ji labarin bangaskiyarku a cikin Yesu Kiristi da kuma \u0199aunar da kuke yi saboda dukan tsarkaka.",
+            "two",
+            null,
+            "ha"
+        ]
+    ],
+    "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": {
+        "num_chars": 64,
+        "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
+        ],
+        "periods_multi_period_discriminator": [
+            2,
+            3,
+            5,
+            7,
+            11
+        ],
+        "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": 2,
+        "speakers_file": "/app/vits_hausa/vits_openbible_hausa-December-28-2024_12+57PM-0000000/speakers.pth",
+        "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,
+        "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": 1.0,
+    "return_wav": true,
+    "use_weighted_sampler": false,
+    "weighted_sampler_attrs": null,
+    "weighted_sampler_multipliers": null,
+    "r": 1,
+    "num_speakers": 0,
+    "use_speaker_embedding": true,
+    "speakers_file": "/app/vits_hausa/vits_openbible_hausa-December-28-2024_12+57PM-0000000/speakers.pth",
+    "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.1735390664.d61ff2a2de12.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:949260085aff84ae17acaa93e58cb07c79f82c620f86fd1187d4d18b9e02d5ec
+size 252997403

events.out.tfevents.1735575309.9797e1bc7ebf.31.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e73262ee81b35018ca93d69b127688e04a75f03741adceae4f0c708868d34513
+size 19884885

events.out.tfevents.1735602988.fc4cf42d63e9.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bccd2e2aeec6d9ba599c80702aaaf3c0074b5575480554c53b0a9c52a766f4c
+size 64342862

events.out.tfevents.1735670635.062b2979dfd5.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f0ffdb9184d643bd5867eef9e72796ac37c9c67094f43a4ef8a0927fe92c11
+size 28576895

speakers.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e8775489aae02f274f540e2a87fa024ceaa315c5d34917f760803b8642807a
+size 864

train_vits.py

@@ -0,0 +1,131 @@
+from trainer import Trainer, TrainerArgs
+
+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, VitsAudioConfig, CharactersConfig
+from TTS.tts.utils.speakers import SpeakerManager
+from TTS.tts.utils.text.tokenizer import TTSTokenizer
+from TTS.utils.audio import AudioProcessor
+
+import os
+import json
+
+output_path = "vits_hausa"
+
+dataset_config = BaseDatasetConfig(
+    meta_file_train="manifest_train.jsonl", meta_file_val="manifest_dev.jsonl", language="ha", path="data"
+)
+
+audio_config = VitsAudioConfig(
+    sample_rate=22050, win_length=1024, hop_length=256, num_mels=80, mel_fmin=0, mel_fmax=None
+)
+
+vitsArgs = VitsArgs(
+    use_speaker_embedding=True,
+)
+
+CHARS = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'R', 'S', 'T', 'U', 'W', 'Y', 'Z', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'r', 's', 't', 'u', 'w', 'y', 'z', 'ā', 'ă', 'ū', 'Ɓ', 'Ɗ', 'Ƙ', 'ƙ', 'ɓ', 'ɗ', '’']
+PUNCT = [' ', '!', "'", ',', '.', ':', ';', '?']
+
+character_config = CharactersConfig(
+    characters_class="TTS.tts.models.vits.VitsCharacters",
+    characters="".join(CHARS),
+    punctuations="".join(PUNCT),
+    pad="<PAD>",
+    eos="<EOS>",
+    bos="<BOS>",
+    blank="<BLNK>",
+)
+
+config = VitsConfig(
+    model_args=vitsArgs,
+    audio=audio_config,
+    run_name="vits_openbible_hausa",
+    run_description="vits_openbible_hausa",
+    batch_size=16,
+    eval_batch_size=16,
+    batch_group_size=48,
+    num_loader_workers=12,
+    num_eval_loader_workers=12,
+    run_eval=True,
+    test_delay_epochs=-1,
+    epochs=1000,
+    text_cleaner="no_cleaners",
+    use_phonemes=False,
+    characters=character_config,
+    compute_input_seq_cache=True,
+    print_step=25,
+    target_loss="loss_1",
+    print_eval=True,
+    save_all_best=True,
+    save_n_checkpoints=10,
+    save_step=5000,
+    mixed_precision=True,
+    max_audio_len=23 * 22050,
+    start_by_longest=True,
+    output_path=output_path,
+    datasets=[dataset_config],
+    cudnn_benchmark=False,
+    test_sentences=[
+        ["Umarnai don zaman tsarki", "two", None, "ha"],
+        ["wanda kuma ya faɗa mana ƙaunar da kuke yi cikin Ruhu.", "one", None, "ha"],
+        ["Gama mun ji labarin bangaskiyarku a cikin Yesu Kiristi da kuma ƙaunar da kuke yi saboda dukan tsarkaka.", "two", None, "ha"],
+    ]
+)
+
+# 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.
+
+def nemo(root_path, meta_file, **kwargs):
+    """
+    Normalizes NeMo-style json manifest files to TTS format
+    """
+    meta_path = os.path.join(root_path, meta_file)
+    items = []
+    with open(meta_path, "r", encoding="utf-8") as ttf:
+        for line in ttf:
+            cols = json.loads(line)
+            wav_file = cols["audio_filepath"]
+            text = cols["text"]
+            speaker_name = cols["speaker_name"] if "speaker_name" in cols else "nemo"
+            language = cols["language"] if "language" in cols else ""
+            items.append({"text": text, "audio_file": wav_file, "speaker_name": speaker_name, "language": language, "root_path": root_path})
+    return items
+
+train_samples, eval_samples = load_tts_samples(dataset_config, formatter=nemo)
+print(f"Loaded {len(train_samples)} train samples")
+print(f"Loaded {len(eval_samples)} eval samples")
+
+# 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_ids_from_data(train_samples + eval_samples, parse_key="speaker_name")
+config.model_args.num_speakers = speaker_manager.num_speakers
+
+# init model
+model = Vits(config, ap, tokenizer, speaker_manager)
+
+# init the trainer and 🚀
+trainer = Trainer(
+    TrainerArgs(),
+    config,
+    output_path,
+    model=model,
+    train_samples=train_samples,
+    eval_samples=eval_samples,
+)
+trainer.fit()

trainer_0_log.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f3e10c1772c97e514119141943e5a1ae5030bcdb99ca49ebb35a8ce48e84c6
+size 16617429