Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 43
+}

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "facebook/mms-tts-yor",
+  "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": 43,
+  "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:e26aae8b3145a85a588e2d49cc3fe6f5051c64915bf8b1ee3905ba57ec9f4bcc
+size 114262646

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054b5410d61aaf9709b782ede793d55c23c8ed90311ad26946b0a727fcc0b7f8
+size 38362603

quantize_config.json

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

special_tokens_map.json

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

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
+    },
+    "43": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "yor",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "|",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1,45 @@
+{
+  " ": 42,
+  "'": 41,
+  "-": 38,
+  "a": 8,
+  "b": 10,
+  "d": 33,
+  "e": 27,
+  "f": 30,
+  "g": 21,
+  "h": 37,
+  "i": 4,
+  "j": 28,
+  "k": 16,
+  "l": 14,
+  "m": 22,
+  "n": 1,
+  "o": 20,
+  "p": 25,
+  "r": 9,
+  "s": 18,
+  "t": 7,
+  "u": 26,
+  "w": 12,
+  "y": 23,
+  "|": 0,
+  "à": 5,
+  "á": 17,
+  "è": 34,
+  "é": 32,
+  "ì": 11,
+  "í": 2,
+  "ò": 29,
+  "ó": 24,
+  "ù": 35,
+  "ú": 19,
+  "ń": 36,
+  "ǹ": 39,
+  "̀": 15,
+  "́": 13,
+  "ṣ": 31,
+  "ẹ": 6,
+  "ọ": 3,
+  "—": 40
+}