Upload 3 files

best_model.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e41a23f5871d17c7a4ea1f60e79ad3a7e2d06e387ba4db2cf5b6c13fcfa1898
+size 343665256

config.json

@@ -0,0 +1,156 @@
+{
+    "model": "glow_tts",
+    "run_name": "coqui_tts",
+    "run_description": "",
+    "epochs": 1000,
+    "batch_size": 128,
+    "eval_batch_size": 16,
+    "mixed_precision": true,
+    "scheduler_after_epoch": false,
+    "run_eval": true,
+    "test_delay_epochs": -1,
+    "print_eval": false,
+    "dashboard_logger": "tensorboard",
+    "print_step": 25,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "project_name": null,
+    "log_model_step": null,
+    "wandb_entity": null,
+    "save_step": 10000,
+    "checkpoint": true,
+    "keep_all_best": false,
+    "keep_after": 10000,
+    "num_loader_workers": 4,
+    "num_eval_loader_workers": 4,
+    "use_noise_augment": false,
+    "use_language_weighted_sampler": false,
+    "output_path": "/media/popos/Barracuda/Models/TTS_new/trained",
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "audio": {
+        "fft_size": 1024,
+        "win_length": 1024,
+        "hop_length": 256,
+        "frame_shift_ms": null,
+        "frame_length_ms": null,
+        "stft_pad_mode": "reflect",
+        "sample_rate": 16000,
+        "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,
+        "signal_norm": true,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": null
+    },
+    "use_phonemes": false,
+    "use_espeak_phonemes": true,
+    "phoneme_language": "it-it",
+    "compute_input_seq_cache": false,
+    "text_cleaner": "phoneme_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/media/popos/Barracuda/Models/TTS_new/trained/phoneme_cache",
+    "characters": {
+        "pad": "_",
+        "eos": "~",
+        "bos": "^",
+        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz",
+        "punctuations": "!'(),-.:;? ",
+        "phonemes": "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\u025a\u02de\u026b",
+        "unique": true
+    },
+    "batch_group_size": 0,
+    "loss_masking": null,
+    "sort_by_audio_len": false,
+    "min_seq_len": 3,
+    "max_seq_len": 500,
+    "compute_f0": false,
+    "compute_linear_spec": false,
+    "add_blank": false,
+    "datasets": [
+        {
+            "name": "ljspeech",
+            "path": "/media/popos/Barracuda/Datasets/MAIL_LABS_TTS/it_IT/by_book/female/lisa_caputo/malavoglia",
+            "meta_file_train": "metadata.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "optimizer": "RAdam",
+    "optimizer_params": {
+        "betas": [
+            0.9,
+            0.998
+        ],
+        "weight_decay": 1e-06
+    },
+    "lr_scheduler": "NoamLR",
+    "lr_scheduler_params": {
+        "warmup_steps": 4000
+    },
+    "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."
+    ],
+    "num_chars": 66,
+    "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
+    },
+    "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,
+    "inference_noise_scale": 0.0,
+    "kernel_size_dec": 5,
+    "dilation_rate": 1,
+    "num_block_layers": 4,
+    "num_speakers": 0,
+    "c_in_channels": 0,
+    "num_splits": 4,
+    "num_squeeze": 2,
+    "sigmoid_scale": false,
+    "d_vector_dim": 0,
+    "data_dep_init_steps": 10,
+    "style_wav_for_test": null,
+    "length_scale": 1.0,
+    "use_speaker_embedding": false,
+    "use_d_vector_file": false,
+    "d_vector_file": false,
+    "grad_clip": 5.0,
+    "lr": 0.001,
+    "r": 1
+}

tts.sh

@@ -0,0 +1,5 @@
+tts --text "È anche un noto pittore e paesaggista greco e conosce trecento opere da collezione."\
+     --model_path "best_model.pth.tar" \
+     --config_path "config.json" \
+     --out_path "italy.wav"
+