Duplicate from LH-Tech-AI/Flare-TTS-v1.5

.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 +1,59 @@
+---
+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 v1.5 28M
+Welcome to Flare-TTS **v1.5** 28M, an open-source text-to-speech model with 28 million parameters trained on LJSpeech.
+<br>
+This is an improved version of Flare-TTS 28M (v1) which is now using a vocoder to remove these robotic sounds!
+
+## Quality and results
+This model has a much better quality now, it doesn't sound robotish anymore and you can clearly understand what the model says.
+<br>
+Example:
+
+
+<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/697f2832c2c5e4daa93cece7/qohVONCxMMh-68Z2U7r46.wav"></audio>
+
+## Training process
+We trained the vocoder for 72 epochs on a single A6000 GPU for ~10 hours. Note that this model is based on the first version Flare-TTS 28M.
+Furthermore, this model now uses a vocoder - see train_vocoder.py for more information and the full code.
+The full training code for the vocoder can be found in this repo as `prepare.sh` and `train_vocoder.py`.
+<br>
+The full pretraining code is here: https://huggingface.co/LH-Tech-AI/Flare-TTS-28M/tree/main
+
+## 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 the second version of Flare-TTS - now with a vocoder. The robot sounds are finally gone!" \
+    --model_path ./model.pth \
+    --config_path ./config.json \
+    --vocoder_path ./vocoder_15000_checkpoint.pth \
+    --vocoder_config_path ./vocoder_config.json \
+    --out_path output_1.wav
+```
+
+## Final thoughts
+This model is much better in the audio quality than the first version of Flare-TTS 28M.
+<br>
+But stay tuned for a third version with more features! :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 +1,13 @@
+# Installs
+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
+wget https://huggingface.co/LH-Tech-AI/Flare-TTS-28M/resolve/main/model.pth
+wget https://huggingface.co/LH-Tech-AI/Flare-TTS-28M/resolve/main/config.json
+
+# Start training
+screen -S vocoder
+PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True python3 train_vocoder.py

train_vocoder.py

@@ -0,0 +1,102 @@
+# train_vocoder.py
+import os
+from trainer import Trainer, TrainerArgs
+from TTS.utils.audio import AudioProcessor
+from TTS.config.shared_configs import BaseAudioConfig
+from TTS.vocoder.configs import HifiganConfig
+from TTS.vocoder.datasets.preprocess import load_wav_data
+from TTS.vocoder.models.gan import GAN
+
+
+def main():
+    output_path = os.path.dirname(os.path.abspath(__file__))
+    data_path = os.path.join(output_path, "LJSpeech-1.1/wavs/")
+
+    audio_config = BaseAudioConfig(
+        sample_rate=22050,
+        resample=False,
+        do_trim_silence=True,
+        trim_db=45,
+
+        fft_size=1024,
+        win_length=1024,
+        hop_length=256,
+        frame_shift_ms=None,
+        frame_length_ms=None,
+
+        num_mels=80,
+        mel_fmin=0.0,
+        mel_fmax=None,
+
+        signal_norm=True,
+        symmetric_norm=True,
+        max_norm=4.0,
+        clip_norm=True,
+        ref_level_db=20,
+        min_level_db=-100,
+        spec_gain=20.0,
+        log_func="np.log10",
+        preemphasis=0.0,
+
+        stats_path=None,
+    )
+
+    config = HifiganConfig(
+        run_name="hifigan_ljspeech",
+        run_description="HiFi-GAN v1 from scratch, GlowTTS-compatible mels",
+
+        data_path=data_path,
+        output_path=output_path,
+        eval_split_size=10,
+
+        audio=audio_config,
+
+        epochs=2000,
+        batch_size=64,
+        eval_batch_size=16,
+        num_loader_workers=4,
+        num_eval_loader_workers=2,
+        run_eval=True,
+        test_delay_epochs=5,
+        mixed_precision=True,
+
+        seq_len=8192,
+        pad_short=2000,
+        use_noise_augment=True,
+
+        lr_gen=2e-4,
+        lr_disc=2e-4,
+
+        print_step=50,
+        print_eval=False,
+        save_step=5000,
+        save_n_checkpoints=5,
+        save_checkpoints=True,
+        log_model_step=10000,
+        plot_step=500,
+    )
+
+    ap = AudioProcessor(config=config.audio)
+
+    eval_samples, train_samples = load_wav_data(
+        config.data_path,
+        config.eval_split_size,
+    )
+
+    model = GAN(config)
+
+    trainer = Trainer(
+        TrainerArgs(),
+        config,
+        output_path,
+        model=model,
+        train_samples=train_samples,
+        eval_samples=eval_samples,
+        training_assets={"audio_processor": ap},
+    )
+
+    trainer.fit()
+
+
+if __name__ == "__main__":
+    main()

vocoder_10000_checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b64d44b94f6c71ad36825528405fb2bea374944cb78b22709260c4dfeddabbde
+size 1016516407

vocoder_15000_checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a6ae4e9c311ea4aef2b44905f81e6b86a9094bd8f1fffb5276429dc75e2482
+size 1016516407

vocoder_5000_checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ade14ee92c9a42f522b852e2a87c7e029722ade94040b85ab34e032e97882e
+size 1016516407

vocoder_7995_checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba221e8f5b210572208c3c504e1d2b5f34ad88836370af51f7c8de5d27c3105
+size 1016516471

vocoder_config.json

@@ -0,0 +1,195 @@
+{
+    "output_path": "/home/ubuntu",
+    "logger_uri": null,
+    "run_name": "hifigan_ljspeech",
+    "project_name": null,
+    "run_description": "HiFi-GAN v1 from scratch, GlowTTS-compatible mels",
+    "print_step": 50,
+    "plot_step": 500,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "save_on_interrupt": true,
+    "log_model_step": 10000,
+    "save_step": 5000,
+    "save_n_checkpoints": 5,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 0,
+    "target_loss": "loss_0",
+    "print_eval": false,
+    "test_delay_epochs": 5,
+    "run_eval": true,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": true,
+    "precision": "fp16",
+    "epochs": 2000,
+    "batch_size": 64,
+    "eval_batch_size": 16,
+    "grad_clip": [
+        5,
+        5
+    ],
+    "scheduler_after_epoch": true,
+    "lr": 0.0001,
+    "optimizer": "AdamW",
+    "optimizer_params": {
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "weight_decay": 0.0
+    },
+    "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": "hifigan",
+    "num_loader_workers": 4,
+    "num_eval_loader_workers": 2,
+    "use_noise_augment": true,
+    "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": 20.0,
+        "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
+    },
+    "eval_split_size": 10,
+    "data_path": "/home/ubuntu/LJSpeech-1.1/wavs/",
+    "feature_path": null,
+    "seq_len": 8192,
+    "pad_short": 2000,
+    "conv_pad": 0,
+    "use_cache": false,
+    "wd": 1e-06,
+    "use_stft_loss": false,
+    "use_subband_stft_loss": false,
+    "use_mse_gan_loss": true,
+    "use_hinge_gan_loss": false,
+    "use_feat_match_loss": true,
+    "use_l1_spec_loss": true,
+    "stft_loss_weight": 0,
+    "subband_stft_loss_weight": 0,
+    "mse_G_loss_weight": 1,
+    "hinge_G_loss_weight": 0,
+    "feat_match_loss_weight": 108,
+    "l1_spec_loss_weight": 45,
+    "stft_loss_params": {
+        "n_ffts": [
+            1024,
+            2048,
+            512
+        ],
+        "hop_lengths": [
+            120,
+            240,
+            50
+        ],
+        "win_lengths": [
+            600,
+            1200,
+            240
+        ]
+    },
+    "l1_spec_loss_params": {
+        "use_mel": true,
+        "sample_rate": 22050,
+        "n_fft": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null
+    },
+    "lr_gen": 0.0002,
+    "lr_disc": 0.0002,
+    "lr_scheduler_gen": "ExponentialLR",
+    "lr_scheduler_gen_params": {
+        "gamma": 0.999,
+        "last_epoch": -1
+    },
+    "lr_scheduler_disc": "ExponentialLR",
+    "lr_scheduler_disc_params": {
+        "gamma": 0.999,
+        "last_epoch": -1
+    },
+    "use_pqmf": false,
+    "steps_to_start_discriminator": 0,
+    "diff_samples_for_G_and_D": false,
+    "discriminator_model": "hifigan_discriminator",
+    "generator_model": "hifigan_generator",
+    "generator_model_params": {
+        "upsample_factors": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "upsample_initial_channel": 512,
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "resblock_type": "1",
+        "in_channels": 80
+    },
+    "github_branch": "inside_docker"
+}