Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 37
+}

checkpoint/checkpoint-322000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86e6428230e9577e90b2d7b41579068b3b81a4b3f8c4fe881fc90e22275d4ec0
+size 145282144

checkpoint/checkpoint-322000/model_1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f353c441de9bed5f56ec02c32d4e4dca74d47b1cd615ca32d92ee97d25354728
+size 187000136

checkpoint/checkpoint-322000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67cb92598aebdabebc6f1de30c39c1bd8bab8d7d773acd9a65654bb65ff6972
+size 291070844

checkpoint/checkpoint-322000/optimizer_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3961ec760ccf47766b4a432bd90101b7ab57752a3a14246e045617ed3c416d24
+size 374071772

checkpoint/checkpoint-322000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23d33dbc5408c38c2b3d0136e8f891e5158a3d68e1c13064d4ac4e023d17436a
+size 14472

checkpoint/checkpoint-322000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32147f54711815745fdc071a8a124294af40c0a2a1f8da6ba05c10c4b8dc4c77
+size 988

checkpoint/checkpoint-322000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d2335ba34af16ab6d827b441ec3b888e7e1f8c320285cafa630de21f796933
+size 1000

checkpoint/checkpoint-322000/scheduler_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54737f9ca6d8fa46a696806ab6e21b11abb7685b5a137d0021440e43b0df094c
+size 1008

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "pytorch_dump",
+  "activation_dropout": 0.1,
+  "architectures": [
+    "VitsModelForPreTraining"
+  ],
+  "attention_dropout": 0.1,
+  "depth_separable_channels": 2,
+  "depth_separable_num_layers": 3,
+  "discriminator_kernel_size": 5,
+  "discriminator_period_channels": [
+    1,
+    32,
+    128,
+    512,
+    1024
+  ],
+  "discriminator_periods": [
+    2,
+    3,
+    5,
+    7,
+    11
+  ],
+  "discriminator_scale_channels": [
+    1,
+    16,
+    64,
+    256,
+    1024
+  ],
+  "discriminator_stride": 3,
+  "duration_predictor_dropout": 0.5,
+  "duration_predictor_filter_channels": 256,
+  "duration_predictor_flow_bins": 10,
+  "duration_predictor_kernel_size": 3,
+  "duration_predictor_num_flows": 4,
+  "duration_predictor_tail_bound": 5.0,
+  "ffn_dim": 768,
+  "ffn_kernel_size": 3,
+  "flow_size": 192,
+  "hidden_act": "relu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 192,
+  "hop_length": 256,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "leaky_relu_slope": 0.1,
+  "model_type": "vits",
+  "noise_scale": 0.667,
+  "noise_scale_duration": 0.8,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 6,
+  "num_speakers": 1,
+  "posterior_encoder_num_wavenet_layers": 16,
+  "prior_encoder_num_flows": 4,
+  "prior_encoder_num_wavenet_layers": 4,
+  "resblock_dilation_sizes": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "resblock_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "sampling_rate": 16000,
+  "segment_size": 8192,
+  "speaker_embedding_size": 0,
+  "speaking_rate": 1.0,
+  "spectrogram_bins": 513,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "upsample_initial_channel": 512,
+  "upsample_kernel_sizes": [
+    16,
+    16,
+    4,
+    4
+  ],
+  "upsample_rates": [
+    8,
+    8,
+    2,
+    2
+  ],
+  "use_bias": true,
+  "use_stochastic_duration_prediction": true,
+  "vocab_size": 37,
+  "wavenet_dilation_rate": 1,
+  "wavenet_dropout": 0.0,
+  "wavenet_kernel_size": 5,
+  "window_size": 4
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90744be4374cf121d6f0d274324f4dc9972389191087fe54cbd0315088d9be56
+size 332159944

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "VitsFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 256,
+  "max_wav_value": 32768.0,
+  "n_fft": 1024,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "pad_token": {
+    "content": "о",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "о",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "ava",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "о",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,39 @@
+{
+  " ": 33,
+  "-": 4,
+  "_": 20,
+  "а": 34,
+  "б": 15,
+  "в": 24,
+  "г": 16,
+  "д": 13,
+  "е": 21,
+  "ж": 8,
+  "з": 5,
+  "и": 30,
+  "й": 23,
+  "к": 31,
+  "л": 12,
+  "м": 11,
+  "н": 1,
+  "о": 0,
+  "п": 2,
+  "р": 35,
+  "с": 17,
+  "т": 29,
+  "у": 18,
+  "ф": 26,
+  "х": 3,
+  "ц": 36,
+  "ч": 25,
+  "ш": 32,
+  "щ": 27,
+  "ъ": 6,
+  "ь": 19,
+  "э": 7,
+  "ю": 9,
+  "я": 14,
+  "ё": 28,
+  "ӏ": 10,
+  "–": 22
+}