New checkpoint

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+dictionary filter=lfs diff=lfs merge=lfs -text

DUR_1000.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f680f319c6cdc83de9c87d4ca63d0112e2e19e81be5699a19430728676e2a54
+oid sha256:7981901d730555ca96a885fbeabd9efb194a1ea9a6083a11c650af36b6032f4b
 size 6693501

D_1000.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c00e69816284dcc68ae3ac956ad2e206127028224650b7578e16bb1e83560e
+oid sha256:fb76d60ae100cb0c882a39c33762faabdc5f03f9134997a27d048acb66904640
 size 561099653

G_1000.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846d6adc7895ef4cb1fc24a927335a665da2678ecfc4455cf5bc8e15bb9d413b
-size 492157086
+oid sha256:9fced69899dfc16e82522aeced259311b72e57df802dc3966a1f742d3e030489
+size 164036245

config.json

@@ -0,0 +1,74 @@
+{
+    "train": {
+      "log_interval": 200,
+      "eval_interval": 1000,
+      "seed": 1234,
+      "epochs": 20000,
+      "learning_rate": 2e-4,
+      "betas": [0.8, 0.99],
+      "eps": 1e-9,
+      "batch_size": 24,
+      "fp16_run": false,
+      "lr_decay": 0.999875,
+      "segment_size": 8192,
+      "init_lr_ratio": 1,
+      "warmup_epochs": 0,
+      "c_mel": 45,
+      "c_kl": 1.0,
+      "fft_sizes": [384, 683, 171],
+      "hop_sizes": [30, 60, 10],
+      "win_lengths": [150, 300, 60],
+      "window": "hann_window"
+    },
+    "data": {
+      "use_mel_posterior_encoder": true,
+      "training_files":"db/metadata-phones-ids.csv.train",
+      "validation_files":"db/metadata-phones-ids.csv.dev",
+      "text_cleaners":[""],
+      "max_wav_value": 32768.0,
+      "sampling_rate": 22050,
+      "filter_length": 1024,
+      "hop_length": 256,
+      "win_length": 1024,
+      "n_mel_channels": 80,
+      "mel_fmin": 0.0,
+      "mel_fmax": null,
+      "add_blank": true,
+      "n_speakers": 5,
+      "cleaned_text": false,
+      "g2p_text": false,
+      "aligned_text": true
+    },
+    "model": {
+      "use_mel_posterior_encoder": true,
+      "use_transformer_flows": true,
+      "transformer_flow_type": "pre_conv2",
+      "use_spk_conditioned_encoder": true,
+      "use_noise_scaled_mas": true,
+      "use_duration_discriminator": true,
+      "duration_discriminator_type": "dur_disc_2",
+      "ms_istft_vits": false,
+      "mb_istft_vits": true,
+      "istft_vits": false,
+      "subbands": 4,
+      "gen_istft_n_fft": 16,
+      "gen_istft_hop_size": 4,
+      "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": [4,4],
+      "upsample_initial_channel": 512,
+      "upsample_kernel_sizes": [16,16],
+      "n_layers_q": 3,
+      "use_spectral_norm": false,
+      "use_sdp": true,
+      "gin_channels": 256
+    }
+}

dictionary

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b31b648edae1df9ed9257e7b9484c38184db01296795e87011debe61b8131231
+size 101434476