Add config files

models/d_vector_model/config.json

@@ -0,0 +1,28 @@
+{
+  "factory": "padertorch.contrib.tcl.speaker_embeddings.dvectors.DVectorModel",
+  "loss": {
+    "eps": 1e-07,
+    "factory": "padertorch.contrib.tcl.speaker_embeddings.loss.AngularPenaltySMLoss",
+    "in_features": 256,
+    "loss_type": "aam",
+    "m": null,
+    "out_features": 7196,
+    "reduce": "mean",
+    "s": null
+  },
+  "sampling_rate": 16000,
+  "speaker_net": {
+    "activation_fn": "relu",
+    "channels": [
+      64,
+      128,
+      256,
+      256
+    ],
+    "dvec_dim": 256,
+    "factory": "padertorch.contrib.tcl.speaker_embeddings.dvectors.ResNet34",
+    "in_channels": 1,
+    "norm": "batch",
+    "pre_activation": true
+  }
+}

models/norm_flow/config.json

@@ -0,0 +1,12 @@
+{
+  "factory": "pvq_manipulation.models.ffjord.FFJORD",
+  "normalize": true,
+  "ode_function": {
+    "condition_dim": 7,
+    "factory": "pvq_manipulation.models.ode_functions.CNFNN",
+    "hidden_channels": [
+      512
+    ],
+    "input_dim": 256
+  }
+}

models/norm_flow/speaker_conditioning.json

@@ -0,0 +1,9 @@
+[
+  "Weight",
+  "Resonance",
+  "Breathiness",
+  "Roughness",
+  "Loudness",
+  "Strain",
+  "Pitch"
+]

models/tts_model/config.json

@@ -0,0 +1,367 @@
+{
+    "output_path": "/net/vol/rautenberg/storage/acoustic_pitch/libritts_r_16",
+    "logger_uri": null,
+    "run_name": "acoustic_pitch",
+    "project_name": "YourTTS",
+    "run_description": "\n                - Original YourTTS trained using VCTK dataset\n            ",
+    "print_step": 50,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "save_on_interrupt": true,
+    "log_model_step": 1000,
+    "save_step": 5000,
+    "save_n_checkpoints": 2,
+    "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,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": false,
+    "precision": "fp16",
+    "epochs": 1000,
+    "batch_size": 50,
+    "eval_batch_size": 50,
+    "grad_clip": [
+        1000,
+        1000,
+        1000
+    ],
+    "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": {},
+    "use_grad_scaler": false,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "vits",
+    "num_loader_workers": 8,
+    "num_eval_loader_workers": 0,
+    "use_noise_augment": false,
+    "audio": {
+        "fft_size": 1024,
+        "sample_rate": 24000,
+        "win_length": 1024,
+        "hop_length": 256,
+        "num_mels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "fading": "half",
+        "window": "hann"
+    },
+    "use_phonemes": false,
+    "phonemizer": "espeak",
+    "phoneme_language": "en",
+    "compute_input_seq_cache": true,
+    "text_cleaner": "multilingual_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "None",
+    "characters": {
+        "characters_class": "TTS.tts.models.vits.VitsCharacters",
+        "vocab_dict": null,
+        "pad": "_",
+        "eos": "&",
+        "bos": "*",
+        "blank": null,
+        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!'(),-.:;?\u00af\u2013\u00fc\u00f6\u00e4\u00df\u201a\u2018\u2019",
+        "punctuations": "!'(),-.:;? ",
+        "phonemes": "",
+        "is_unique": true,
+        "is_sorted": true
+    },
+    "add_blank": true,
+    "batch_group_size": 48,
+    "loss_masking": null,
+    "min_audio_len": 1,
+    "max_audio_len": 240000,
+    "min_text_len": 1,
+    "max_text_len": Infinity,
+    "compute_f0": false,
+    "compute_energy": false,
+    "compute_linear_spec": true,
+    "precompute_num_workers": 12,
+    "start_by_longest": true,
+    "shuffle": false,
+    "drop_last": false,
+    "datasets": null,
+    "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.",
+            "/net/vol/rautenberg/storage/Dataset/librittsr/LibriTTS_R/test-clean/1089/134686/1089_134686_000001_000001.wav",
+            "1089",
+            "1089_134686_000001_000001"
+        ],
+        [
+            "Be a voice, not an echo.",
+            "/net/vol/rautenberg/storage/Dataset/librittsr/LibriTTS_R/test-clean/1089/134691/1089_134691_000004_000001.wav",
+            "1089",
+            "1089_134691_000004_000001"
+        ],
+        [
+            "I'm sorry Dave. I'm afraid I can't do that.",
+            "/net/vol/rautenberg/storage/Dataset/librittsr/LibriTTS_R/test-clean/121/127105/121_127105_000024_000000.wav",
+            "121",
+            "121_127105_000024_000000"
+        ],
+        [
+            "This cake is great. It's so delicious and moist.",
+            "/net/vol/rautenberg/storage/Dataset/librittsr/LibriTTS_R/test-clean/1284/1181/1284_1181_000005_000000.wav",
+            "1284",
+            "1284_1181_000005_000000"
+        ]
+    ],
+    "eval_split_max_size": 256,
+    "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": 84,
+        "out_channels": 513,
+        "spec_segment_size": 64,
+        "hidden_channels": 192,
+        "hidden_channels_ffn_text_encoder": 768,
+        "num_heads_text_encoder": 2,
+        "num_layers_text_encoder": 10,
+        "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": false,
+        "noise_scale": 1.0,
+        "inference_noise_scale": 0.667,
+        "length_scale": 1,
+        "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": false,
+        "num_speakers": 0,
+        "speakers_file": "/net/vol/rautenberg/storage/acoustic_pitch/libritts_r_16/acoustic_pitch-July-15-2024_04+08PM-1471536/speakers.pth",
+        "d_vector_file": null,
+        "speaker_embedding_channels": 256,
+        "use_d_vector_file": true,
+        "d_vector_dim": 256,
+        "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": "./models/d_vector_model/config_se.json",
+        "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,
+    "feat_loss_alpha": 1.0,
+    "mel_loss_alpha": 45.0,
+    "dur_loss_alpha": 1.0,
+    "speaker_encoder_loss_alpha": 9.0,
+    "return_wav": true,
+    "use_weighted_sampler": true,
+    "weighted_sampler_attrs": {
+        "speaker_name": 1.0
+    },
+    "weighted_sampler_multipliers": {},
+    "r": 1,
+    "num_speakers": 0,
+    "use_speaker_embedding": false,
+    "speakers_file": "/net/vol/rautenberg/storage/acoustic_pitch/libritts_r_16/acoustic_pitch-July-15-2024_04+08PM-1471536/speakers.pth",
+    "speaker_embedding_channels": 256,
+    "language_ids_file": null,
+    "use_language_embedding": false,
+    "d_vectors_stor_file": false,
+    "d_vector_model_file": "./models/d_vector_model/",
+    "d_vector_dim": 256,
+    "d_vector_model": "nt_model",
+    "dataset_dict": {
+        "datasets": {
+            "libritts_r": {
+                "dataset_storage_path": "/net/vol/rautenberg/storage/Dataset/librittsr/",
+                "d_vector_storage_file": "/net/vol/rautenberg/storage/Dataset/d_vectors_libritts_r/nt",
+                "phone_alignement_path": "Phone_alignement/libri_tts_aligned/",
+                "hubert_features_storage_file": "/net/vol/rautenberg/storage/Dataset/hubert_libritts_r/nt",
+                "creak_labels_storage_file": "/net/vol/rautenberg/storage/Dataset/creak_labels/libritts_r/mean"
+            }
+        },
+        "test_sentences": [
+            {
+                "text": "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
+                "audio_path": "/net/vol/rautenberg/storage/Dataset/librittsr/LibriTTS_R/test-clean/1089/134686/1089_134686_000001_000001.wav",
+                "speaker_id": "1089",
+                "example_id": "1089_134686_000001_000001",
+                "manipulation_times": [
+                    0.4,
+                    0.7,
+                    1
+                ],
+                "manipulation_factors": [
+                    0,
+                    0.5,
+                    1
+                ],
+                "manipulation_idx": [
+                    0
+                ],
+                "dataset_name": "libritts_r"
+            },
+            {
+                "text": "Be a voice, not an echo.",
+                "audio_path": "/net/vol/rautenberg/storage/Dataset/librittsr/LibriTTS_R/test-clean/1089/134691/1089_134691_000004_000001.wav",
+                "speaker_id": "1089",
+                "example_id": "1089_134691_000004_000001",
+                "manipulation_times": [
+                    0.4,
+                    0.7,
+                    1
+                ],
+                "manipulation_factors": [
+                    0,
+                    0.5,
+                    1
+                ],
+                "manipulation_idx": [
+                    0
+                ],
+                "dataset_name": "libritts_r"
+            },
+            {
+                "text": "I'm sorry Dave. I'm afraid I can't do that.",
+                "audio_path": "/net/vol/rautenberg/storage/Dataset/librittsr/LibriTTS_R/test-clean/121/127105/121_127105_000024_000000.wav",
+                "speaker_id": "121",
+                "example_id": "121_127105_000024_000000",
+                "manipulation_times": [
+                    0.4,
+                    0.7,
+                    1
+                ],
+                "manipulation_factors": [
+                    0,
+                    0.5,
+                    1
+                ],
+                "manipulation_idx": [
+                    0
+                ],
+                "dataset_name": "libritts_r"
+            },
+            {
+                "text": "This cake is great. It's so delicious and moist.",
+                "audio_path": "/net/vol/rautenberg/storage/Dataset/librittsr/LibriTTS_R/test-clean/1284/1181/1284_1181_000005_000000.wav",
+                "speaker_id": "1284",
+                "example_id": "1284_1181_000005_000000",
+                "manipulation_times": [
+                    0.4,
+                    0.7,
+                    1
+                ],
+                "manipulation_factors": [
+                    0,
+                    0.5,
+                    1
+                ],
+                "manipulation_idx": [
+                    0
+                ],
+                "dataset_name": "libritts_r"
+            }
+        ]
+    },
+    "sample_rate": 24000,
+    "use_vad": false,
+    "CONFIG_SOLVER": "",
+    "use_speaker_embedding_cond": true
+}