Upload 5 files

fastpitch/best_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669f75b7a9f64f07fb516e62ff6c2e39ecf71e8dff9d52bd0993960eb633145a
+size 637332589

fastpitch/config.json

@@ -0,0 +1,210 @@
+{
+    "output_path": "output_indic_fastpitch/ml",
+    "logger_uri": null,
+    "run_name": "ml_fastpitch_indictts_all_align_off",
+    "project_name": "indic-fastpitch-stage2",
+    "run_description": "align_off",
+    "print_step": 100,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": "indic-asr",
+    "dashboard_logger": "wandb",
+    "log_model_step": 10000,
+    "save_step": 10000,
+    "save_n_checkpoints": 1,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 10000,
+    "target_loss": null,
+    "print_eval": false,
+    "test_delay_epochs": 0,
+    "run_eval": true,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": true,
+    "epochs": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 32,
+    "grad_clip": 5.0,
+    "scheduler_after_epoch": true,
+    "lr": 0.0001,
+    "optimizer": "Adam",
+    "optimizer_params": {
+        "betas": [
+            0.9,
+            0.998
+        ],
+        "weight_decay": 1e-06
+    },
+    "lr_scheduler": "NoamLR",
+    "lr_scheduler_params": {
+        "warmup_steps": 4000
+    },
+    "use_grad_scaler": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "fast_pitch",
+    "num_loader_workers": 0,
+    "num_eval_loader_workers": 0,
+    "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.log",
+        "do_trim_silence": true,
+        "trim_db": 60.0,
+        "do_rms_norm": false,
+        "db_level": null,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": 8000,
+        "spec_gain": 1.0,
+        "do_amp_to_db_linear": true,
+        "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": "en-us",
+    "compute_input_seq_cache": false,
+    "text_cleaner": "multilingual_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "output_indic_fastpitch/ml/phoneme_cache",
+    "characters": {
+        "characters_class": "TTS.tts.models.vits.VitsCharacters",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": " ,?\u0d02\u0d03\u0d05\u0d06\u0d07\u0d08\u0d09\u0d0a\u0d0b\u0d0e\u0d0f\u0d10\u0d12\u0d13\u0d14\u0d15\u0d16\u0d17\u0d18\u0d19\u0d1a\u0d1b\u0d1c\u0d1d\u0d1e\u0d1f\u0d20\u0d21\u0d22\u0d23\u0d24\u0d25\u0d26\u0d27\u0d28\u0d2a\u0d2b\u0d2c\u0d2d\u0d2e\u0d2f\u0d30\u0d31\u0d32\u0d33\u0d34\u0d35\u0d36\u0d37\u0d38\u0d39\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d43\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0d4d\u0d57\u0d7a\u0d7b\u0d7c\u0d7d\u0d7e",
+        "punctuations": "!\u00a1'(),-.:;\u00bf? ",
+        "phonemes": null,
+        "is_unique": true,
+        "is_sorted": true
+    },
+    "add_blank": false,
+    "batch_group_size": 0,
+    "loss_masking": null,
+    "sort_by_audio_len": true,
+    "min_audio_len": 1,
+    "max_audio_len": 441000,
+    "min_text_len": 1,
+    "max_text_len": 400,
+    "compute_f0": true,
+    "compute_linear_spec": false,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "datasets": [
+        {
+            "name": "indictts",
+            "path": "/home/ttsteam/datasets/indictts/ml",
+            "meta_file_train": "metadata_train.csv",
+            "ignored_speakers": null,
+            "language": "ml",
+            "meta_file_val": "metadata_test.csv",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        "\u0d36\u0d3f\u0d32\u0d3e\u0d2f\u0d41\u0d17\u0d15\u0d3e\u0d32\u0d02 \u0d2e\u0d41\u0d24\u0d7d \u0d2e\u0d28\u0d41\u0d37\u0d4d\u0d2f\u0d7c \u0d1c\u0d4d\u0d2f\u0d3e\u0d2e\u0d3f\u0d24\u0d40\u0d2f \u0d30\u0d42\u0d2a\u0d19\u0d4d\u0d19\u0d7e \u0d09\u0d2a\u0d2f\u0d4b\u0d17\u0d3f\u0d1a\u0d4d\u0d1a\u0d41\u0d35\u0d30\u0d41\u0d28\u0d4d\u0d28\u0d41",
+        "\u0d35\u0d3e\u0d39\u0d28\u0d3e\u0d2a\u0d15\u0d1f\u0d24\u0d4d\u0d24\u0d3f\u0d7d \u0d2a\u0d30\u0d41\u0d15\u0d4d\u0d15\u0d47\u0d31\u0d4d\u0d31 \u0d05\u0d27\u0d4d\u0d2f\u0d3e\u0d2a\u0d3f\u0d15 \u0d2e\u0d30\u0d3f\u0d1a\u0d4d\u0d1a\u0d41"
+    ],
+    "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,
+    "base_model": "forward_tts",
+    "model_args": {
+        "num_chars": 88,
+        "out_channels": 80,
+        "hidden_channels": 512,
+        "use_aligner": true,
+        "use_pitch": true,
+        "pitch_predictor_hidden_channels": 256,
+        "pitch_predictor_kernel_size": 3,
+        "pitch_predictor_dropout_p": 0.1,
+        "pitch_embedding_kernel_size": 3,
+        "duration_predictor_hidden_channels": 256,
+        "duration_predictor_kernel_size": 3,
+        "duration_predictor_dropout_p": 0.1,
+        "positional_encoding": true,
+        "poisitonal_encoding_use_scale": true,
+        "length_scale": 1,
+        "encoder_type": "fftransformer",
+        "encoder_params": {
+            "hidden_channels_ffn": 1024,
+            "num_heads": 1,
+            "num_layers": 6,
+            "dropout_p": 0.1
+        },
+        "decoder_type": "fftransformer",
+        "decoder_params": {
+            "hidden_channels_ffn": 1024,
+            "num_heads": 1,
+            "num_layers": 6,
+            "dropout_p": 0.1
+        },
+        "detach_duration_predictor": false,
+        "max_duration": 75,
+        "num_speakers": 2,
+        "use_speaker_embedding": true,
+        "speakers_file": "models/v1/ml/fastpitch/speakers.pth",
+        "use_d_vector_file": false,
+        "d_vector_dim": 512,
+        "d_vector_file": null,
+        "use_speaker_encoder_as_loss": false,
+        "speaker_encoder_config_path": "",
+        "speaker_encoder_model_path": "",
+        "vocoder_path": null,
+        "vocoder_config_path": null
+    },
+    "return_wav": false,
+    "num_speakers": 2,
+    "speakers_file": "models/v1/ml/fastpitch/speakers.pth",
+    "use_speaker_embedding": true,
+    "use_d_vector_file": false,
+    "d_vector_file": "",
+    "d_vector_dim": 512,
+    "spec_loss_type": "mse",
+    "duration_loss_type": "mse",
+    "use_ssim_loss": false,
+    "ssim_loss_alpha": 1.0,
+    "spec_loss_alpha": 1.0,
+    "aligner_loss_alpha": 1.0,
+    "pitch_loss_alpha": 0.1,
+    "dur_loss_alpha": 0.1,
+    "binary_align_loss_alpha": 0.1,
+    "spk_encoder_loss_alpha": 0.1,
+    "binary_loss_warmup_epochs": 150,
+    "aligner_epochs": 0,
+    "min_seq_len": 13,
+    "max_seq_len": 500000,
+    "r": 1,
+    "f0_cache_path": "output_indic_fastpitch/ml/f0_cache"
+}

fastpitch/speakers.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f665e358b34b232fb27f7c8cd3968fcd47784a7be065ae127f611c33ee809bea
+size 431

hifigan/best_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba37e31c72f088cd6d73c5782d9f89bf024a6d355158056fa398cd806cf8efc
+size 1016384316

hifigan/config.json

@@ -0,0 +1,189 @@
+{
+    "output_path": "indic_vocoders",
+    "logger_uri": null,
+    "run_name": "ml_hifigan_all",
+    "project_name": "indic-vocoders",
+    "run_description": "None",
+    "print_step": 100,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": "indic-asr",
+    "dashboard_logger": "wandb",
+    "log_model_step": null,
+    "save_step": 10000,
+    "save_n_checkpoints": 1,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 10000,
+    "target_loss": "loss_1",
+    "print_eval": false,
+    "test_delay_epochs": 0,
+    "run_eval": true,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:10008",
+    "mixed_precision": true,
+    "epochs": 5000,
+    "batch_size": 32,
+    "eval_batch_size": 32,
+    "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": null,
+    "use_grad_scaler": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "hifigan",
+    "num_loader_workers": 8,
+    "num_eval_loader_workers": 8,
+    "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.log",
+        "do_trim_silence": true,
+        "trim_db": 60.0,
+        "do_rms_norm": false,
+        "db_level": null,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": 8000,
+        "spec_gain": 1.0,
+        "do_amp_to_db_linear": true,
+        "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
+    },
+    "eval_split_size": 10,
+    "data_path": "../../datasets/indictts/ml",
+    "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": 0.0001,
+    "lr_disc": 0.0001,
+    "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,
+    "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"
+    },
+    "github_branch": "* main"
+}