Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 95
+}

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "facebook/mms-tts-vie",
+  "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": 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,
+  "speaker_embedding_size": 0,
+  "speaking_rate": 1.0,
+  "spectrogram_bins": 513,
+  "transformers_version": "4.37.0.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": 95,
+  "wavenet_dilation_rate": 1,
+  "wavenet_dropout": 0.0,
+  "wavenet_kernel_size": 5,
+  "window_size": 4
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a2ae2279440a38b244cfbd4a7abe968d6f4ae0e4dfb1844f666c396cafa482
+size 114302582

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6bafa09857a76f798ea312f2b5bc45a29a42960e0920cf1cf7dd081c353db4
+size 38372589

quantize_config.json

@@ -0,0 +1,61 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "MatMul",
+                "Add",
+                "Pow",
+                "Less",
+                "Tanh",
+                "Squeeze",
+                "Mul",
+                "RandomNormalLike",
+                "Transpose",
+                "Equal",
+                "Relu",
+                "Cast",
+                "Split",
+                "Erf",
+                "Greater",
+                "Softplus",
+                "Not",
+                "Range",
+                "Ceil",
+                "Clip",
+                "ReduceMax",
+                "Sqrt",
+                "ConstantOfShape",
+                "And",
+                "ScatterND",
+                "ReduceMean",
+                "Softmax",
+                "ReduceSum",
+                "Conv",
+                "Shape",
+                "CumSum",
+                "Slice",
+                "Unsqueeze",
+                "Concat",
+                "Div",
+                "GatherND",
+                "Where",
+                "Gather",
+                "Neg",
+                "Exp",
+                "Reshape",
+                "LeakyRelu",
+                "Sigmoid",
+                "ConvTranspose",
+                "Expand",
+                "Sub",
+                "Pad",
+                "Constant",
+                "NonZero",
+                "GatherElements"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "ụ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "95": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "vie",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "ụ",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1,97 @@
+{
+  " ": 84,
+  "'": 44,
+  "-": 94,
+  "2": 52,
+  "_": 17,
+  "a": 29,
+  "b": 88,
+  "c": 13,
+  "d": 63,
+  "e": 54,
+  "g": 21,
+  "h": 85,
+  "i": 30,
+  "k": 79,
+  "l": 82,
+  "m": 68,
+  "n": 90,
+  "o": 31,
+  "p": 78,
+  "q": 47,
+  "r": 92,
+  "s": 2,
+  "t": 80,
+  "u": 8,
+  "v": 14,
+  "x": 1,
+  "y": 75,
+  "à": 35,
+  "á": 77,
+  "â": 12,
+  "ã": 51,
+  "è": 3,
+  "é": 58,
+  "ê": 91,
+  "ì": 4,
+  "í": 74,
+  "ò": 45,
+  "ó": 56,
+  "ô": 28,
+  "õ": 25,
+  "ù": 38,
+  "ú": 76,
+  "ý": 37,
+  "ă": 89,
+  "đ": 55,
+  "ĩ": 23,
+  "ũ": 70,
+  "ơ": 7,
+  "ư": 9,
+  "ạ": 22,
+  "ả": 24,
+  "ấ": 81,
+  "ầ": 57,
+  "ẩ": 49,
+  "ẫ": 67,
+  "ậ": 87,
+  "ắ": 65,
+  "ằ": 10,
+  "ẳ": 27,
+  "ẵ": 42,
+  "ặ": 5,
+  "ẹ": 72,
+  "ẻ": 20,
+  "ẽ": 66,
+  "ế": 60,
+  "ề": 40,
+  "ể": 69,
+  "ễ": 41,
+  "ệ": 15,
+  "ỉ": 71,
+  "ị": 53,
+  "ọ": 48,
+  "ỏ": 43,
+  "ố": 46,
+  "ồ": 16,
+  "ổ": 34,
+  "ỗ": 73,
+  "ộ": 19,
+  "ớ": 59,
+  "ờ": 36,
+  "ở": 83,
+  "ỡ": 26,
+  "ợ": 93,
+  "ụ": 0,
+  "ủ": 61,
+  "ứ": 6,
+  "ừ": 32,
+  "ử": 62,
+  "ữ": 64,
+  "ự": 50,
+  "ỳ": 11,
+  "ỵ": 18,
+  "ỷ": 86,
+  "ỹ": 33,
+  "–": 39
+}