Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 53
+}

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "./vits-cmn",
+  "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,
+  "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": 44,
+  "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,
+  "transformers_version": "4.36.2",
+  "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": 53,
+  "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 sha256:6f64defc393b53a54a1ad923c457f87e88179fc90a0186a958b27b5a2c6fb409
+size 158691200

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6cf71c28ac68d5943750626fd73cdc3a3ae5ab761a919bfe061a542f0c2688
+size 114225562

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179b0f4aa84e99b0667a759cce5ba974c622f0045e8e0bd0e7adb669cabab785
+size 38343972

quantize_config.json

@@ -0,0 +1,62 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Softmax",
+                "Split",
+                "Concat",
+                "Transpose",
+                "Pow",
+                "Relu",
+                "Div",
+                "Softplus",
+                "ConstantOfShape",
+                "Cast",
+                "Sub",
+                "Expand",
+                "LeakyRelu",
+                "MatMul",
+                "ReduceSum",
+                "Exp",
+                "Sqrt",
+                "Not",
+                "GatherND",
+                "GatherElements",
+                "Add",
+                "Equal",
+                "Where",
+                "Tanh",
+                "And",
+                "LessOrEqual",
+                "Erf",
+                "ScatterND",
+                "Squeeze",
+                "CumSum",
+                "ConvTranspose",
+                "Gather",
+                "Mul",
+                "Less",
+                "Ceil",
+                "Pad",
+                "Clip",
+                "Shape",
+                "Reshape",
+                "LayerNormalization",
+                "Conv",
+                "RandomNormalLike",
+                "Unsqueeze",
+                "ReduceMax",
+                "Sigmoid",
+                "Constant",
+                "Range",
+                "Neg",
+                "Slice",
+                "GreaterOrEqual",
+                "NonZero"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,111 @@
+{
+    "version": "1.0",
+    "truncation": null,
+    "padding": null,
+    "added_tokens": [
+        {
+            "id": 53,
+            "content": "<unk>",
+            "single_word": false,
+            "lstrip": false,
+            "rstrip": false,
+            "normalized": false,
+            "special": true
+        }
+    ],
+    "normalizer": {
+        "type": "Sequence",
+        "normalizers": [
+            {
+                "type": "Lowercase"
+            },
+            {
+                "type": "Replace",
+                "pattern": {
+                    "Regex": "[^_ abcdefghijklmnopqrstuwxyz\u00e0\u00e1\u00e8\u00e9\u00ec\u00ed\u00f2\u00f3\u00f9\u00fa\u00fc\u0101\u0113\u011b\u012b\u0144\u014d\u016b\u01ce\u01d0\u01d2\u01d4\u01d8\u01da\u01dc\u1e3f]"
+                },
+                "content": ""
+            },
+            {
+                "type": "Strip",
+                "strip_left": true,
+                "strip_right": true
+            },
+            {
+                "type": "Replace",
+                "pattern": {
+                    "Regex": "(?=.)|(?<!^)$"
+                },
+                "content": "_"
+            }
+        ]
+    },
+    "pre_tokenizer": {
+        "type": "Split",
+        "pattern": {
+            "Regex": ""
+        },
+        "behavior": "Isolated",
+        "invert": false
+    },
+    "post_processor": null,
+    "decoder": null,
+    "model": {
+        "vocab": {
+            "_": 0,
+            " ": 1,
+            "a": 2,
+            "b": 3,
+            "c": 4,
+            "d": 5,
+            "e": 6,
+            "f": 7,
+            "g": 8,
+            "h": 9,
+            "i": 10,
+            "j": 11,
+            "k": 12,
+            "l": 13,
+            "m": 14,
+            "n": 15,
+            "o": 16,
+            "p": 17,
+            "q": 18,
+            "r": 19,
+            "s": 20,
+            "t": 21,
+            "u": 22,
+            "w": 23,
+            "x": 24,
+            "y": 25,
+            "z": 26,
+            "\u00e0": 27,
+            "\u00e1": 28,
+            "\u00e8": 29,
+            "\u00e9": 30,
+            "\u00ec": 31,
+            "\u00ed": 32,
+            "\u00f2": 33,
+            "\u00f3": 34,
+            "\u00f9": 35,
+            "\u00fa": 36,
+            "\u00fc": 37,
+            "\u0101": 38,
+            "\u0113": 39,
+            "\u011b": 40,
+            "\u012b": 41,
+            "\u0144": 42,
+            "\u014d": 43,
+            "\u016b": 44,
+            "\u01ce": 45,
+            "\u01d0": 46,
+            "\u01d2": 47,
+            "\u01d4": 48,
+            "\u01d8": 49,
+            "\u01da": 50,
+            "\u01dc": 51,
+            "\u1e3f": 52,
+            "<unk>": 53
+        }
+    }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "53": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "cmn",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "_",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1,55 @@
+{
+  " ": 1,
+  "_": 0,
+  "a": 2,
+  "b": 3,
+  "c": 4,
+  "d": 5,
+  "e": 6,
+  "f": 7,
+  "g": 8,
+  "h": 9,
+  "i": 10,
+  "j": 11,
+  "k": 12,
+  "l": 13,
+  "m": 14,
+  "n": 15,
+  "o": 16,
+  "p": 17,
+  "q": 18,
+  "r": 19,
+  "s": 20,
+  "t": 21,
+  "u": 22,
+  "w": 23,
+  "x": 24,
+  "y": 25,
+  "z": 26,
+  "à": 27,
+  "á": 28,
+  "è": 29,
+  "é": 30,
+  "ì": 31,
+  "í": 32,
+  "ò": 33,
+  "ó": 34,
+  "ù": 35,
+  "ú": 36,
+  "ü": 37,
+  "ā": 38,
+  "ē": 39,
+  "ě": 40,
+  "ī": 41,
+  "ń": 42,
+  "ō": 43,
+  "ū": 44,
+  "ǎ": 45,
+  "ǐ": 46,
+  "ǒ": 47,
+  "ǔ": 48,
+  "ǘ": 49,
+  "ǚ": 50,
+  "ǜ": 51,
+  "ḿ": 52
+}