Upload 6 files

bark.json

@@ -0,0 +1,107 @@
+{
+ "train": {
+ "log_interval": 200,
+ "eval_interval": 800,
+ "seed": 1234,
+ "epochs": 10000,
+ "learning_rate": 0.0004,
+ "betas": [
+ 0.8,
+ 0.99
+ ],
+ "eps": 1e-09,
+ "batch_size": 16,
+ "fp16_run": false,
+ "half_type": "fp16",
+ "lr_decay": 0.999875,
+ "segment_size": 10240,
+ "init_lr_ratio": 1,
+ "warmup_epochs": 0,
+ "c_mel": 45,
+ "c_kl": 1.0,
+ "use_sr": true,
+ "max_speclen": 512,
+ "port": "8001",
+ "keep_ckpts": 0,
+ "all_in_mem": false,
+ "vol_aug": true
+ },
+ "data": {
+ "training_files": "filelists/train.txt",
+ "validation_files": "filelists/val.txt",
+ "max_wav_value": 32768.0,
+ "sampling_rate": 44100,
+ "filter_length": 2048,
+ "hop_length": 512,
+ "win_length": 2048,
+ "n_mel_channels": 80,
+ "mel_fmin": 0.0,
+ "mel_fmax": 22050,
+ "unit_interpolate_mode": "nearest"
+ },
+ "model": {
+ "inter_channels": 192,
+ "hidden_channels": 192,
+ "filter_channels": 768,
+ "n_heads": 2,
+ "n_layers": 6,
+ "kernel_size": 3,
+ "p_dropout": 0.1,
+ "resblock": "1",
+ "resblock_kernel_sizes": [
+ 3,
+ 7,
+ 11
+ ],
+ "resblock_dilation_sizes": [
+ [
+ 1,
+ 3,
+ 5
+ ],
+ [
+ 1,
+ 3,
+ 5
+ ],
+ [
+ 1,
+ 3,
+ 5
+ ]
+ ],
+ "upsample_rates": [
+ 8,
+ 8,
+ 2,
+ 2,
+ 2
+ ],
+ "upsample_initial_channel": 512,
+ "upsample_kernel_sizes": [
+ 16,
+ 16,
+ 4,
+ 4,
+ 4
+ ],
+ "n_layers_q": 3,
+ "n_flow_layer": 4,
+ "use_spectral_norm": false,
+ "gin_channels": 768,
+ "ssl_dim": 768,
+ "n_speakers": 3,
+ "vocoder_name": "nsf-hifigan",
+ "speech_encoder": "vec768l12",
+ "speaker_embedding": false,
+ "vol_embedding": true,
+ "use_depthwise_conv": false,
+ "flow_share_parameter": false,
+ "use_automatic_f0_prediction": true
+ },
+ "spk": {
+ "ferocious": 0,
+ "husky": 1,
+ "puppy": 2
+ }
+}

bark.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea95a730092bae5145d8619eac9dae7787a2bd6126ff0263005e093ff411af4
+size 160943725

diffusion.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0d6eeee43658c6afb9d8553f999f9bfb59cb3a61bdbed513dd428f4bc4372f8
+size 220897161

diffusion.yaml

@@ -0,0 +1,53 @@
+data:
+ block_size: 512
+ cnhubertsoft_gate: 10
+ duration: 2
+ encoder: vec768l12
+ encoder_hop_size: 320
+ encoder_out_channels: 768
+ encoder_sample_rate: 16000
+ extensions:
+ - wav
+ sampling_rate: 44100
+ training_files: filelists/train.txt
+ unit_interpolate_mode: nearest
+ validation_files: filelists/val.txt
+device: cuda
+env:
+ expdir: logs/44k/diffusion
+ gpu_id: 0
+infer:
+ method: dpm-solver++
+ speedup: 10
+model:
+ k_step_max: 0
+ n_chans: 512
+ n_hidden: 256
+ n_layers: 20
+ n_spk: 3
+ timesteps: 1000
+ type: Diffusion
+ use_pitch_aug: true
+spk:
+ ferocious: 0
+ husky: 1
+ puppy: 2
+train:
+ amp_dtype: fp32
+ batch_size: 48
+ cache_all_data: true
+ cache_device: cpu
+ cache_fp16: true
+ decay_step: 100000
+ epochs: 100000
+ gamma: 0.5
+ interval_force_save: 5000
+ interval_log: 10
+ interval_val: 2000
+ lr: 0.0001
+ num_workers: 4
+ save_opt: false
+ weight_decay: 0
+vocoder:
+ ckpt: pretrain/nsf_hifigan/model
+ type: nsf-hifigan

feature_and_index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d94ebcec894746f5506dae365c7e898632c266dc645295aee4a6ef468665c0f4
+size 94026795

kmeans.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246f46790f42a354d5162f97b0e4a119ac04bbf9272d3eb9a508cd8908880488
+size 93411321