Added ONNX converted model using Xenova script

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 30
+}

config.json

@@ -0,0 +1,84 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "facebook/mms-tts-mlg",
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0.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": 30,
+  "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:a256cb95f9a22f859ec13e402e6849e76de9da539c140e5c9ebdd9c653446a2c
+size 114220325

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,88 @@
+{
+    "version": "1.0",
+    "truncation": null,
+    "padding": null,
+    "added_tokens": [
+        {
+            "id": 30,
+            "content": "<unk>",
+            "single_word": false,
+            "lstrip": false,
+            "rstrip": false,
+            "normalized": false,
+            "special": true
+        }
+    ],
+    "normalizer": {
+        "type": "Sequence",
+        "normalizers": [
+            {
+                "type": "Lowercase"
+            },
+            {
+                "type": "Replace",
+                "pattern": {
+                    "Regex": "[^a|niyortmehskfzdl'vpbj\\-g\u00e0\u1ef3\u00f4\u00f2\u00ec ]"
+                },
+                "content": ""
+            },
+            {
+                "type": "Strip",
+                "strip_left": true,
+                "strip_right": true
+            },
+            {
+                "type": "Replace",
+                "pattern": {
+                    "Regex": "(?=.)|(?<!^)$"
+                },
+                "content": "a"
+            }
+        ]
+    },
+    "pre_tokenizer": {
+        "type": "Split",
+        "pattern": {
+            "Regex": ""
+        },
+        "behavior": "Isolated",
+        "invert": false
+    },
+    "post_processor": null,
+    "decoder": null,
+    "model": {
+        "vocab": {
+            "a": 0,
+            "|": 1,
+            "n": 2,
+            "i": 3,
+            "y": 4,
+            "o": 5,
+            "r": 6,
+            "t": 7,
+            "m": 8,
+            "e": 9,
+            "h": 10,
+            "s": 11,
+            "k": 12,
+            "f": 13,
+            "z": 14,
+            "d": 15,
+            "l": 16,
+            "'": 17,
+            "v": 18,
+            "p": 19,
+            "b": 20,
+            "j": 21,
+            "-": 22,
+            "g": 23,
+            "\u00e0": 24,
+            "\u1ef3": 25,
+            "\u00f4": 26,
+            "\u00f2": 27,
+            "\u00ec": 28,
+            " ": 29,
+            "<unk>": 30
+        }
+    }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "a",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "extra_special_tokens": {},
+  "is_uroman": false,
+  "language": "mlg",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "a",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1,32 @@
+{
+  " ": 29,
+  "'": 17,
+  "-": 22,
+  "a": 0,
+  "b": 20,
+  "d": 15,
+  "e": 9,
+  "f": 13,
+  "g": 23,
+  "h": 10,
+  "i": 3,
+  "j": 21,
+  "k": 12,
+  "l": 16,
+  "m": 8,
+  "n": 2,
+  "o": 5,
+  "p": 19,
+  "r": 6,
+  "s": 11,
+  "t": 7,
+  "v": 18,
+  "y": 4,
+  "z": 14,
+  "|": 1,
+  "à": 24,
+  "ì": 28,
+  "ò": 27,
+  "ô": 26,
+  "ỳ": 25
+}