Upload 5 files

config.json

@@ -0,0 +1,86 @@
+{
+  "activation_dropout": 0.1,
+  "architectures": [
+    "VitsModel"
+  ],
+  "attention_dropout": 0.1,
+  "depth_separable_channels": 2,
+  "depth_separable_num_layers": 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,
+  "encoder_attention_heads": 2,
+  "encoder_ffn_dim": 768,
+  "encoder_layerdrop": 0.1,
+  "encoder_layers": 6,
+  "ffn_dim": 768,
+  "ffn_kernel_size": 3,
+  "flow_size": 192,
+  "hidden_act": "relu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 192,
+  "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": 2,
+  "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,
+  "speaker_embedding_size": 256,
+  "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": 55,
+  "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:a174a410ed115315f704d0b32ba2bf99e4de5a162b98cd03a862803475fb7279
+size 158653176

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "pad_token": "~",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_blank": true,
+  "clean_up_tokenization_spaces": true,
+  "language": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "~",
+  "phonemize": false,
+  "tokenizer_class": "ezVitsTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1,55 @@
+{"~": 0,
+  "^":  1,
+  "$":  2,
+  "?":  3,
+  "!":  4,
+  "_":  5,
+  "#":  6,
+  "[":  7,
+  "]":  8, 
+  "A":  9,
+  "E":  10,
+  "I":  11,
+  "N":  12,
+  "O":  13,
+  "U":  14,
+  "a":  15,
+  "b":  16,
+  "by": 17,
+  "ch": 18,
+  "cl": 19,
+  "d":  20,
+  "dy": 21,
+  "e":  22,
+  "f":  23,
+  "g":  24,
+  "gy": 25,
+  "gw": 26,
+  "h":  27,
+  "hy": 28,
+  "i":  29,
+  "j":  30,
+  "k":  31,
+  "ky": 32,
+  "kw": 33,
+  "m":  34,
+  "my": 35,
+  "n":  36,
+  "ny": 37,
+  "o":  38,
+  "p":  39,
+  "py": 40,
+  "r":  41,
+  "ry": 42,
+  "s":  43,
+  "sh": 44,
+  "t":  45,
+  "ts": 46,
+  "ty": 47,
+  "u":  48,
+  "v":  49,
+  "w":  50,
+  "y":  51,
+  "z":  52,
+  "pau": 53,
+  "sil": 54, "<unk>": 0}