Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 75
+}

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "facebook/mms-tts-kan",
+  "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": "4.43.4",
+  "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": 75,
+  "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:e0365f4af5056ceb112c2cd410287606c540393a146351026637ed4d388adf75
+size 114072750

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c90363416344ecf4b553258dbbf4f05a5e50f6ebd71e2cbc6e03b2bb77e64198
+size 111035209

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03bc0fd0bdcc9dba1b1559617c11699329f2c326215ba2aabaa1057019f982f6
+size 57515945

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c400d05b3dce87a9601b2ba0e034140e4cca7f186566ab28b249f30933951b
+size 37744174

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d19d500dec146bbdc0044f79af2a4d3420052bf7243ed28b92c198ec3d6d08d
+size 111090313

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bcbfa1235e5324c716337f3b6330bc7596f97911500f9c7579af78eb3d1f321
+size 56247684

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff7ed92052c33c82ece808785775928b708247c3a1c530ecbea25b8b0f244c4b
+size 37744174

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff7ed92052c33c82ece808785775928b708247c3a1c530ecbea25b8b0f244c4b
+size 37744174

quantize_config.json

@@ -0,0 +1,17 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": true,
+    "reduce_range": true,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,133 @@
+{
+    "version": "1.0",
+    "truncation": null,
+    "padding": null,
+    "added_tokens": [
+        {
+            "id": 75,
+            "content": "<unk>",
+            "single_word": false,
+            "lstrip": false,
+            "rstrip": false,
+            "normalized": false,
+            "special": true
+        }
+    ],
+    "normalizer": {
+        "type": "Sequence",
+        "normalizers": [
+            {
+                "type": "Lowercase"
+            },
+            {
+                "type": "Replace",
+                "pattern": {
+                    "Regex": "[^'\u0c93\u0cae\u0c86\u0cad\u0c8b\u0c9a\u0c9f\u0cc1\u0cc7\u0c9c\u0c8f\u0cbe\u0caa\u0cb6\u0ccd\u0c88\u0c94\u0c9e1\u0ca8\u0c8e\u0cb8\u0cb5\u0c87\u0c985\u0c8a\u0cb3\u0c96\u0cc3\u0cc6\\-\u0ca4\u0c9d\u0ca2 \u0c85\u0ca7\u0ccc\u0cb9\u0caf9\u0cab\u0c9b86\u0cb2\u0ca3_\u0ca6\u0cac\u0ca0\u0ca1\u0c833\u0ccb\u0c82\u0c92\u0cc0\u0c95\u0cbf\u0ca5\u0cb0\u0cc2\u0c90\u0cc8\u0c8920\u0c97\u0cca\u0cb747]"
+                },
+                "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,
+            "\u0c93": 1,
+            "\u0cae": 2,
+            "\u0c86": 3,
+            "\u0cad": 4,
+            "\u0c8b": 5,
+            "\u0c9a": 6,
+            "\u0c9f": 7,
+            "\u0cc1": 8,
+            "\u0cc7": 9,
+            "\u0c9c": 10,
+            "\u0c8f": 11,
+            "\u0cbe": 12,
+            "\u0caa": 13,
+            "\u0cb6": 14,
+            "\u0ccd": 15,
+            "\u0c88": 16,
+            "\u0c94": 17,
+            "\u0c9e": 18,
+            "1": 19,
+            "\u0ca8": 20,
+            "\u0c8e": 21,
+            "\u0cb8": 22,
+            "\u0cb5": 23,
+            "\u0c87": 24,
+            "\u0c98": 25,
+            "5": 26,
+            "\u0c8a": 27,
+            "\u0cb3": 28,
+            "\u0c96": 29,
+            "\u0cc3": 30,
+            "\u0cc6": 31,
+            "-": 32,
+            "\u0ca4": 33,
+            "\u0c9d": 34,
+            "\u0ca2": 35,
+            " ": 36,
+            "\u0c85": 37,
+            "\u0ca7": 38,
+            "\u0ccc": 39,
+            "\u0cb9": 40,
+            "\u0caf": 41,
+            "9": 42,
+            "\u0cab": 43,
+            "\u0c9b": 44,
+            "8": 45,
+            "6": 46,
+            "\u0cb2": 47,
+            "\u0ca3": 48,
+            "_": 49,
+            "\u0ca6": 50,
+            "\u0cac": 51,
+            "\u0ca0": 52,
+            "\u0ca1": 53,
+            "\u0c83": 54,
+            "3": 55,
+            "\u0ccb": 56,
+            "\u0c82": 57,
+            "\u0c92": 58,
+            "\u0cc0": 59,
+            "\u0c95": 60,
+            "\u0cbf": 61,
+            "\u0ca5": 62,
+            "\u0cb0": 63,
+            "\u0cc2": 64,
+            "\u0c90": 65,
+            "\u0cc8": 66,
+            "\u0c89": 67,
+            "2": 68,
+            "0": 69,
+            "\u0c97": 70,
+            "\u0cca": 71,
+            "\u0cb7": 72,
+            "4": 73,
+            "7": 74,
+            "<unk>": 75
+        }
+    }
+}

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
+    },
+    "75": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "kan",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "'",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1,77 @@
+{
+  " ": 36,
+  "'": 0,
+  "-": 32,
+  "0": 69,
+  "1": 19,
+  "2": 68,
+  "3": 55,
+  "4": 73,
+  "5": 26,
+  "6": 46,
+  "7": 74,
+  "8": 45,
+  "9": 42,
+  "_": 49,
+  "ಂ": 57,
+  "ಃ": 54,
+  "ಅ": 37,
+  "ಆ": 3,
+  "ಇ": 24,
+  "ಈ": 16,
+  "ಉ": 67,
+  "ಊ": 27,
+  "ಋ": 5,
+  "ಎ": 21,
+  "ಏ": 11,
+  "ಐ": 65,
+  "ಒ": 58,
+  "ಓ": 1,
+  "ಔ": 17,
+  "ಕ": 60,
+  "ಖ": 29,
+  "ಗ": 70,
+  "ಘ": 25,
+  "ಚ": 6,
+  "ಛ": 44,
+  "ಜ": 10,
+  "ಝ": 34,
+  "ಞ": 18,
+  "ಟ": 7,
+  "ಠ": 52,
+  "ಡ": 53,
+  "ಢ": 35,
+  "ಣ": 48,
+  "ತ": 33,
+  "ಥ": 62,
+  "ದ": 50,
+  "ಧ": 38,
+  "ನ": 20,
+  "ಪ": 13,
+  "ಫ": 43,
+  "ಬ": 51,
+  "ಭ": 4,
+  "ಮ": 2,
+  "ಯ": 41,
+  "ರ": 63,
+  "ಲ": 47,
+  "ಳ": 28,
+  "ವ": 23,
+  "ಶ": 14,
+  "ಷ": 72,
+  "ಸ": 22,
+  "ಹ": 40,
+  "ಾ": 12,
+  "ಿ": 61,
+  "ೀ": 59,
+  "ು": 8,
+  "ೂ": 64,
+  "ೃ": 30,
+  "ೆ": 31,
+  "ೇ": 9,
+  "ೈ": 66,
+  "ೊ": 71,
+  "ೋ": 56,
+  "ೌ": 39,
+  "್": 15
+}