Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 60
+}

config.json

@@ -0,0 +1,107 @@
+{
+  "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": "4.36.0.dev0",
+  "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": 60,
+  "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:caca7c0366db7ad083917a98bd7d1ecf134fe706ae15ab1894e6df354eeaeed7
+size 332174408

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 +1,4 @@
+{
+  "pad_token": "|",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "60": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "guj",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "|",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,62 @@
+{
+  " ": 59,
+  "'": 47,
+  "-": 56,
+  "|": 0,
+  "ં": 10,
+  "ઃ": 54,
+  "અ": 28,
+  "આ": 26,
+  "ઇ": 49,
+  "ઈ": 30,
+  "ઉ": 42,
+  "ઊ": 48,
+  "ઋ": 57,
+  "એ": 29,
+  "ઐ": 58,
+  "ઓ": 27,
+  "ક": 9,
+  "ખ": 33,
+  "ગ": 32,
+  "ઘ": 44,
+  "ચ": 39,
+  "છ": 23,
+  "જ": 18,
+  "ઝ": 51,
+  "ઞ": 50,
+  "ટ": 36,
+  "ઠ": 45,
+  "ડ": 40,
+  "ઢ": 52,
+  "ણ": 22,
+  "ત": 3,
+  "થ": 19,
+  "દ": 25,
+  "ધ": 34,
+  "ન": 4,
+  "પ": 12,
+  "ફ": 43,
+  "બ": 31,
+  "ભ": 35,
+  "મ": 7,
+  "ય": 16,
+  "ર": 5,
+  "લ": 24,
+  "ળ": 37,
+  "વ": 13,
+  "શ": 21,
+  "ષ": 41,
+  "સ": 15,
+  "હ": 17,
+  "ા": 1,
+  "િ": 20,
+  "ી": 8,
+  "ુ": 14,
+  "ૂ": 38,
+  "ૃ": 46,
+  "ે": 2,
+  "ૈ": 53,
+  "ો": 11,
+  "ૌ": 55,
+  "્": 6
+}