Add TeraTTS ONNX release artifacts

.gitattributes

@@ -1,2 +1,5 @@
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.npy filter=lfs diff=lfs merge=lfs -text
+ruaccent/dictionary/accents.json.gz filter=lfs diff=lfs merge=lfs -text
+ruaccent/dictionary/omographs.json.gz filter=lfs diff=lfs merge=lfs -text
+ruaccent/dictionary/yo_words.json.gz filter=lfs diff=lfs merge=lfs -text

models/duration_predictor.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15248b4751493fe48543f01164cd9b74d103b4483c63367a01c344442ebf03d8
+size 1572411

models/sampler_distilled_cfg3_8step.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e496d23538fb22fcb726034544bc409f19cd5cd97621d8712afe9e344e1ec4a3
+size 256417627

models/sampler_teacher_8step.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1390ff3449cf50f79a15543888022d13c5fa86398713bf42da56e74f023bbf82
+size 256528334

models/text_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8966b3d2267d891f9329c1750481c4685b3e22b098a75c512d06d714a4e5ef05
+size 27910297

models/vocoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e4cf9a9b9de8cca28f309c4cb7735327322b5a764ba61dfc3706c3c7942c07
+size 101416199

ruaccent/dictionary/accents.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa460ebba90de00fbbf3d41d121961f605b98667e45efb7920f127473b15515e
+size 20954156

ruaccent/dictionary/omographs.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a9e81c68d65f65ba493fe0110f99e79087548c2beeec3032e2b66e28706f36
+size 219047

ruaccent/dictionary/yo_words.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19fa89a964a0691d9fe4ee384783e3934904891843d8f59a1c480d67947a82a
+size 548914

ruaccent/nn/nn_accent/big.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47e69d9ae19f2a82e21b1c70f6a4bbfb1abc5759e98b2e67d009c5e9d7af18c9
+size 2285217

ruaccent/nn/nn_accent/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "onnx_out",
+  "architectures": [
+    "RoFormerForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.2,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "NO",
+    "1": "STRESS_PRIMARY",
+    "2": "STRESS_SECONDARY"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "label2id": {
+    "NO": 0,
+    "STRESS_PRIMARY": 1,
+    "STRESS_SECONDARY": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_length": 40,
+  "max_position_embeddings": 60,
+  "max_relative_positions": 60,
+  "model_type": "roformer",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "relative_attention": true,
+  "rotary_value": false,
+  "transformers_version": "4.29.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 45
+}

ruaccent/nn/nn_accent/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e393144e45626f6f1062a0784ef06f921b97321a8e7b87ac2a09a892286500a
+size 803402

ruaccent/nn/nn_accent/ort_config.json

@@ -0,0 +1,30 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "optimum_version": "1.8.5",
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QOperator",
+    "is_static": false,
+    "mode": "IntegerOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "MatMul",
+      "Add"
+    ],
+    "per_channel": false,
+    "qdq_add_pair_to_weight": false,
+    "qdq_dedicated_pair": false,
+    "qdq_op_type_per_channel_support_to_axis": {
+      "MatMul": 1
+    },
+    "reduce_range": false,
+    "weights_dtype": "QInt8",
+    "weights_symmetric": true
+  },
+  "transformers_version": "4.29.2",
+  "use_external_data_format": false
+}

ruaccent/nn/nn_accent/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "[bos]",
+  "eos_token": "[eos]",
+  "pad_token": "[pad]",
+  "unk_token": "[unk]"
+}

ruaccent/nn/nn_accent/tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token": "[bos]",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "[eos]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[pad]",
+  "tokenizer_class": "CharTokenizer",
+  "unk_token": "[unk]"
+}

ruaccent/nn/nn_accent/vocab.txt

@@ -0,0 +1,45 @@
+[pad]
+[unk]
+[bos]
+[eos]
+'
+-
+.
+?
+`
+c
+e
+́
+а
+б
+в
+г
+д
+е
+ж
+з
+и
+й
+к
+л
+м
+н
+о
+п
+р
+с
+т
+у
+ф
+х
+ц
+ч
+ш
+щ
+ъ
+ы
+ь
+э
+ю
+я
+ё

ruaccent/nn/nn_omograph/turbo3.1/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "turbo4_1/",
+  "architectures": [
+    "DebertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": null,
+  "position_biased_input": true,
+  "relative_attention": false,
+  "transformers_version": "4.29.1",
+  "type_vocab_size": 0,
+  "vocab_size": 60258
+}

ruaccent/nn/nn_omograph/turbo3.1/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb6a174c4cdb45bd3132b4f7c8a3779fc4b6869863180ed7d0e421bcd453dbd
+size 359306923

ruaccent/nn/nn_omograph/turbo3.1/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

ruaccent/nn/nn_omograph/turbo3.1/tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

ruaccent/nn/nn_stress_usage_predictor/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "tiny/checkpoint-59441/",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "NO_STRESS",
+    "1": "PUNCT",
+    "2": "STRESS"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "NO_STRESS": 0,
+    "PUNCT": 1,
+    "STRESS": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.28.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

ruaccent/nn/nn_stress_usage_predictor/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d547500637b4ddfec8880ed6d1405fd50ee9d3f0131ef8a2a69dcf961dbefeb
+size 116473561

ruaccent/nn/nn_stress_usage_predictor/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

ruaccent/nn/nn_stress_usage_predictor/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 2048,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

ruaccent/nn/nn_yo_homograph_resolver/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "5k/",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 264,
+  "dropout": 0.1,
+  "hidden_dim": 792,
+  "id2label": {
+    "0": "NO_YO",
+    "1": "PUNCT",
+    "2": "YO"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NO_YO": 0,
+    "PUNCT": 1,
+    "YO": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 3,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "transformers_version": "4.29.2",
+  "vocab_size": 5031
+}

ruaccent/nn/nn_yo_homograph_resolver/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42cc85bf0c4b319dfe3d89fa17b162a92fd5e1c651a657cb3d5f44978d4e70ac
+size 14332169

ruaccent/nn/nn_yo_homograph_resolver/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

ruaccent/nn/nn_yo_homograph_resolver/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

styles/en_female/style_dp.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e99de1badbe70e56da671d2c27dccbfc2caeeb0fd71e80f9532df1811b8fcf40
+size 640

styles/en_female/style_ttl.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d859b839a1cdb8e3204032b34719b63b7746da552f45d867d2eb72dd632067
+size 51328

styles/en_male/style_dp.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e6b87cfe57922b868096b7b4cecb87003cc096b177dbd6034c400ae8e437e6
+size 640

styles/en_male/style_ttl.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47efa51c3059b0eb5fd2a32f9dad1f7580808a1c95ff4d8bbd6c1b71fbf7244c
+size 51328

styles/masha_ls/style_dp.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c10c8c3e6f9016e4ff625425450b99772a9246ffed6b062d236f23863b27d1
+size 640

styles/masha_ls/style_ttl.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c1d3f7644d1250355400950fca234ddf3867c3fd8fc24bc6e153f81a3bf317
+size 51328

styles/mita/style_dp.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189e1eabfccf8f0f76a6b10d84ba0fdde18de2ecc2c2e16e3a790f961db95382
+size 640

styles/mita/style_ttl.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bafbfbe93efe2e4a87e2365282e13fbab7ab6faaccea61e8d8258488f57435f6
+size 51328

styles/ru_female/style_dp.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:477b15db0dc2c5b2ab7794ffc1a8c6c6ae2e0881cc6865fb0da74de63445de96
+size 640

styles/ru_female/style_ttl.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f698b258230d56cce4bc344ff75ac789161dc25393cc6c44b82b119b9b7e9c5
+size 51328

styles/ru_male/style_dp.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7bb78f77d4e88027e363b6d97402f0e493c4fd51b1aeb109371c4bab68ffe6
+size 640

styles/ru_male/style_ttl.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb75241f50286775de651047da65f9a074f465c5336e26ada43626d15fe82581
+size 51328