Upload 13 files

diffwave/args.json

@@ -0,0 +1,282 @@
+{
+    "base_config": "egs/vocoder/diffusion/exp_config_base.json",
+    "dataset": [
+        "csd",
+        "m4singer",
+        "opencpop",
+        "opensinger",
+        "pjs",
+        "popcs",
+        "ljspeech",
+        "vctk",
+    ],
+    "dataset_path": {
+        "csd": "[dataset path]",
+        "kising": "[dataset path]",
+        "libritts": "[dataset path]",
+        "ljspeech": "[dataset path]",
+        "m4singer": "[dataset path]",
+        "nus48e": "[dataset path]",
+        "opencpop": "[dataset path]",
+        "opensinger": "[dataset path]",
+        "opera": "[dataset path]",
+        "pjs": "[dataset path]",
+        "popbutfy": "[dataset path]",
+        "popcs": "[dataset path]",
+        "vctk": "[dataset path]",
+    },
+    "exp_name": "diff_pretrain_2",
+    "inference": {
+        "batch_size": 1,
+    },
+    "log_dir": "ckpts/vocoder",
+    "model": {
+        "diffwave": {
+            "dilation_cycle_length": 10,
+            "inference_noise_schedule": [
+                0.0001,
+                0.001,
+                0.01,
+                0.05,
+                0.2,
+                0.5,
+            ],
+            "noise_schedule": [
+                0.0001,
+                0.0011183673469387756,
+                0.002136734693877551,
+                0.0031551020408163264,
+                0.004173469387755102,
+                0.005191836734693878,
+                0.006210204081632653,
+                0.007228571428571429,
+                0.008246938775510203,
+                0.009265306122448979,
+                0.010283673469387754,
+                0.01130204081632653,
+                0.012320408163265305,
+                0.013338775510204081,
+                0.014357142857142857,
+                0.015375510204081632,
+                0.016393877551020408,
+                0.017412244897959183,
+                0.01843061224489796,
+                0.019448979591836734,
+                0.02046734693877551,
+                0.021485714285714285,
+                0.02250408163265306,
+                0.023522448979591836,
+                0.02454081632653061,
+                0.025559183673469387,
+                0.026577551020408163,
+                0.027595918367346938,
+                0.028614285714285714,
+                0.02963265306122449,
+                0.030651020408163265,
+                0.031669387755102044,
+                0.03268775510204082,
+                0.033706122448979595,
+                0.03472448979591837,
+                0.035742857142857146,
+                0.03676122448979592,
+                0.0377795918367347,
+                0.03879795918367347,
+                0.03981632653061225,
+                0.04083469387755102,
+                0.0418530612244898,
+                0.042871428571428574,
+                0.04388979591836735,
+                0.044908163265306125,
+                0.0459265306122449,
+                0.046944897959183676,
+                0.04796326530612245,
+                0.04898163265306123,
+                0.05,
+            ],
+            "noise_schedule_factors": [
+                0.0001,
+                0.05,
+                50,
+            ],
+            "residual_channels": 64,
+            "residual_layers": 30,
+            "upsample_factors": [
+                16,
+                16,
+            ],
+        },
+        "generator": "diffwave",
+    },
+    "model_type": "DiffusionVocoder",
+    "preprocess": {
+        "align_mel_duration": false,
+        "audio_dir": "audios",
+        "bits": 8,
+        "contentvec_dir": "contentvec",
+        "cut_mel_frame": 32,
+        "data_augment": false,
+        "dur_dir": "durs",
+        "duration_dir": "duration",
+        "emo2id": "emo2id.json",
+        "energy_dir": "energys",
+        "energy_extract_mode": "from_mel",
+        "energy_norm": false,
+        "energy_remove_outlier": false,
+        "extract_acoustic_token": false,
+        "extract_amplitude_phase": false,
+        "extract_audio": true,
+        "extract_contentvec_feature": false,
+        "extract_duration": false,
+        "extract_energy": false,
+        "extract_label": false,
+        "extract_linear_spec": false,
+        "extract_mcep": false,
+        "extract_mel": true,
+        "extract_mert_feature": false,
+        "extract_one_hot": false,
+        "extract_phone": false,
+        "extract_pitch": false,
+        "extract_uv": false,
+        "extract_wenet_feature": false,
+        "extract_whisper_feature": false,
+        "f0_max": 1100,
+        "f0_min": 50,
+        "file_lst": "file.lst",
+        "fmax": 12000,
+        "fmin": 0,
+        "hop_size": 256,
+        "imaginary_dir": "imaginarys",
+        "is_mu_law": false,
+        "lab_dir": "labs",
+        "label_dir": "labels",
+        "lexicon_path": "./text/lexicon/librispeech-lexicon.txt",
+        "linear_dir": "linears",
+        "log_amplitude_dir": "log_amplitudes",
+        "mcep_dir": "mcep",
+        "mel_dir": "mels",
+        "mel_extract_mode": "",
+        "mel_min_max_norm": false,
+        "min_level_db": -115,
+        "n_fft": 1024,
+        "n_mel": 100,
+        "num_silent_frames": 8,
+        "phase_dir": "phases",
+        "phone_dir": "phones",
+        "phone_energy_dir": "phone_energys",
+        "phone_extractor": "espeak",
+        "phone_pitch_dir": "phone_pitches",
+        "phone_seq_file": "phone_seq_file",
+        "pitch_bin": 256,
+        "pitch_dir": "pitches",
+        "pitch_extractor": "parselmouth",
+        "pitch_max": 1100.0,
+        "pitch_min": 50.0,
+        "pitch_norm": false,
+        "pitch_remove_outlier": false,
+        "processed_dir": "/mnt/data1/wangyuancheng/vocoder-processed",
+        "raw_data": "raw_data",
+        "real_dir": "reals",
+        "ref_level_db": 20,
+        "sample_rate": 24000,
+        "spk2id": "singers.json",
+        "symbols_dict": "symbols.dict",
+        "train_file": "train.json",
+        "trim_fft_size": 512,
+        "trim_hop_size": 128,
+        "trim_silence": false,
+        "trim_top_db": 30,
+        "trimmed_wav_dir": "trimmed_wavs",
+        "use_amplitude_phase": false,
+        "use_audio": true,
+        "use_dur": false,
+        "use_emoid": false,
+        "use_frame_duration": false,
+        "use_frame_energy": false,
+        "use_frame_pitch": false,
+        "use_lab": false,
+        "use_label": false,
+        "use_linear": false,
+        "use_log_scale_energy": false,
+        "use_log_scale_pitch": false,
+        "use_mel": true,
+        "use_min_max_norm_mel": false,
+        "use_one_hot": false,
+        "use_phn_seq": false,
+        "use_phone": false,
+        "use_phone_duration": false,
+        "use_phone_energy": false,
+        "use_phone_pitch": false,
+        "use_spkid": false,
+        "use_text": false,
+        "use_uv": false,
+        "use_wav": false,
+        "use_wenet": false,
+        "utt2emo": "utt2emo",
+        "utt2spk": "utt2spk",
+        "uv_dir": "uvs",
+        "valid_file": "test.json",
+        "wav_dir": "wavs",
+        "wenet_dir": "wenet",
+        "win_size": 1024,
+    },
+    "supported_model_type": [
+        "GANVocoder",
+        "Fastspeech2",
+        "DiffSVC",
+        "Transformer",
+        "EDM",
+        "CD",
+    ],
+    "task_type": "vocoder",
+    "train": {
+        "adamw": {
+            "adam_b1": 0.8,
+            "adam_b2": 0.99,
+            "lr": 0.0002,
+        },
+        "batch_size": 64,
+        "dataloader": {
+            "num_worker": 16,
+            "pin_memory": true,
+        },
+        "ddp": true,
+        "exponential_lr": {
+            "lr_decay": 0.999,
+        },
+        "gradient_accumulation_step": 1,
+        "keep_checkpoint_max": 5,
+        "keep_last": [
+            3,
+            -1,
+        ],
+        "max_epoch": 1000000,
+        "max_steps": 1000000,
+        "multi_speaker_training": false,
+        "optimizer": "AdamW",
+        "random_seed": 114514,
+        "reducelronplateau": {
+            "factor": 0.8,
+            "min_lr": 0.0001,
+            "patience": 10,
+        },
+        "run_eval": [
+            true,
+        ],
+        "sampler": {
+            "drop_last": true,
+            "holistic_shuffle": true,
+        },
+        "save_checkpoint_stride": [
+            20,
+        ],
+        "save_checkpoints_steps": 10000,
+        "save_summary_steps": 500,
+        "scheduler": "ReduceLROnPlateau",
+        "total_training_steps": 50000,
+        "tracker": [
+            "tensorboard",
+        ],
+        "valid_interval": 10000,
+    },
+    "use_custom_dataset": false,
+}

diffwave/checkpoint/epoch-1980_step-1311424_loss-0.036577/ckpts.json

@@ -0,0 +1,3 @@
+[
+    []
+]

diffwave/checkpoint/epoch-1980_step-1311424_loss-0.036577/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:427605c2d934e8937928f8d2254fafcdd125da1ef0868e5348c5789f6ce4841d
+size 21789125

diffwave/checkpoint/epoch-1980_step-1311424_loss-0.036577/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ab7ca33830d4d208eba6223ec53990103a3930062048da5be1c6071f3122fe
+size 10881477

diffwave/checkpoint/epoch-1980_step-1311424_loss-0.036577/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcecee435a25c95277795387d98a545b91a56030dfacea3e15f3380f0430c8d7
+size 17683

diffwave/checkpoint/epoch-1980_step-1311424_loss-0.036577/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc48780e11ee11f948d6a344c8ed36341812b3ee3aa1f5c6fe5f9afd199ca78
+size 563