Duplicate from LH-Tech-AI/Flare-TTS-28M

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,49 @@
+---
+language:
+- en
+pipeline_tag: text-to-speech
+tags:
+- tts
+- flare
+- open
+- open-source
+- small
+- speech
+- text-to-speech
+- tiny
+- cpu
+datasets:
+- keithito/lj_speech
+---
+
+# 🎙️ Flare-TTS 28M
+Welcome to Flare-TTS 28M, an open-source text-to-speech model with 28 million parameters trained on LJSpeech.
+
+## Quality and results
+This model is okayish quality but it still sounds a bit robotish but you can clearly understand what the model tries to say.
+See this model as a proof-of-concept or a first-beta.
+Example:
+<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/697f2832c2c5e4daa93cece7/vluuHSnp9Ietk7Uk1-hvG.mpga"></audio>
+
+## Training process
+We trained this model for ~300 epochs on a single A6000 GPU for ~24 hours.
+The full training code can be found in this repo as `start.sh` and `train.py`. Just run `start.sh` to train this model yourself.
+
+## Architecture
+This model was trained using CoquiTTS. For the architecture we chose GlowTTS.
+
+## Training dataset
+We trained on the full LJSpeech dataset. Thanks to keithito for this :-)
+
+## How to use
+As soon as you have the model checkpoint (`model.pth`) and `config.json` on your device, you can generate a sample using:
+```bash
+tts --text "Hello world, this is my first trained TTS model." \
+    --model_path model.pth \
+    --config_path config.json \
+    --out_path output_1.wav
+```
+
+## Final thoughts
+We don't think it's perfect - it's more like a proof of concept. So please do not use this model for production use cases but more for experiments.
+We are happy to share more of this soon - stay tuned for Flare-TTS v2 :D

config.json

@@ -0,0 +1,198 @@
+{
+    "output_path": "/home/ubuntu",
+    "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",
+    "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": 600,
+    "batch_size": 256,
+    "eval_batch_size": 128,
+    "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": 4,
+    "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
+    },
+    "model_args": {},
+    "_supports_cloning": false,
+    "languages": [
+        "en-us"
+    ],
+    "speakers": [],
+    "use_phonemes": true,
+    "phonemizer": "espeak",
+    "phoneme_language": "en-us",
+    "compute_input_seq_cache": false,
+    "text_cleaner": "phoneme_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/home/ubuntu/phoneme_cache",
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.IPAPhonemes",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "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": 22050,
+    "max_audio_len": 220500,
+    "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": "/home/ubuntu/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,
+    "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,
+    "kernel_size_dec": 5,
+    "dilation_rate": 1,
+    "num_block_layers": 4,
+    "c_in_channels": 0,
+    "num_splits": 4,
+    "num_squeeze": 2,
+    "sigmoid_scale": false,
+    "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
+    },
+    "d_vector_dim": 0,
+    "data_dep_init_steps": 10,
+    "style_wav_for_test": null,
+    "inference_noise_scale": 0.0,
+    "length_scale": 1.0,
+    "use_speaker_embedding": false,
+    "speakers_file": null,
+    "use_d_vector_file": false,
+    "d_vector_file": null,
+    "min_seq_len": 3,
+    "max_seq_len": 500,
+    "r": 1,
+    "github_branch": "inside_docker"
+}

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e49ef2cc522d6f5fad8b6bd6932cfaf8bc42ea22911d9d63ffbdda951a44f3
+size 343850470

prepare.sh

@@ -0,0 +1,7 @@
+pip install git+https://github.com/idiap/coqui-tts.git
+sudo apt update && sudo apt install espeak -y
+sudo apt install ffmpeg libavcodec-dev libavformat-dev libavutil-dev -y
+pip install "coqui-tts[codec]"
+wget https://data.keithito.com/data/speech/LJSpeech-1.1.tar.bz2
+tar -xjf LJSpeech-1.1.tar.bz2
+PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True python3 train_glowtts.py

train_glowtts.py

@@ -0,0 +1,71 @@
+import os
+import inspect
+from trainer import Trainer, TrainerArgs
+from TTS.tts.configs.glow_tts_config import GlowTTSConfig
+from TTS.tts.models.glow_tts import GlowTTS
+from TTS.tts.configs.shared_configs import BaseDatasetConfig
+from TTS.tts.datasets import load_tts_samples
+from TTS.tts.utils.text.tokenizer import TTSTokenizer
+from TTS.utils.audio import AudioProcessor
+
+def main():
+    output_path = os.path.dirname(os.path.abspath(__file__))
+
+    dataset_config = BaseDatasetConfig(
+        formatter="ljspeech",
+        meta_file_train="metadata.csv",
+        path=os.path.join(output_path, "LJSpeech-1.1/")
+    )
+
+    config = GlowTTSConfig(
+        batch_size=256,
+        eval_batch_size=128,
+        num_loader_workers=4,
+        num_eval_loader_workers=2,
+        run_eval=True,
+        test_delay_epochs=-1,
+        epochs=600,
+        text_cleaner="phoneme_cleaners",
+        use_phonemes=True,
+        phoneme_language="en-us",
+        phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
+        print_step=25,
+        print_eval=False,
+        mixed_precision=True,
+        output_path=output_path,
+        datasets=[dataset_config],
+	    max_audio_len=22050 * 10,
+        min_audio_len=22050 * 1,
+    )
+
+    ap = AudioProcessor(config=config.audio)
+
+    tokenizer, config = TTSTokenizer.init_from_config(config)
+
+    train_samples, eval_samples = load_tts_samples(
+        config,
+        eval_split=True,
+        eval_split_max_size=20,
+    )
+
+    model = GlowTTS(config, ap, tokenizer=tokenizer, speaker_manager=None)
+
+    trainer = Trainer(
+        TrainerArgs(),
+        config,
+        output_path,
+        model=model,
+        train_samples=train_samples,
+        eval_samples=eval_samples,
+        training_assets={'audio_processor': ap},
+    )
+
+    if getattr(trainer, "best_loss", None) is None:
+        trainer.best_loss = {"train_loss": float("inf")}
+    elif isinstance(trainer.best_loss, dict) and trainer.best_loss.get("train_loss") is None:
+        trainer.best_loss["train_loss"] = float("inf")
+
+    trainer.fit()
+
+if __name__ == "__main__":
+    main()