Duplicate from ekhodzitsky/rupunct-small-onnx

Co-authored-by: Evgeny Khodzitsky <ekhodzitsky@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,36 @@
+---
+license: mit
+language:
+- ru
+base_model: RUPunct/RUPunct_small
+tags:
+- onnx
+- punctuation
+- capitalization
+- russian
+- token-classification
+library_name: onnxruntime
+---
+
+# RUPunct_small — INT8 ONNX
+
+INT8-quantized ONNX export of [RUPunct/RUPunct_small](https://huggingface.co/RUPunct/RUPunct_small)
+(MIT) — Russian **punctuation + capitalization restoration** as token classification.
+
+Packaged for use in the [gigastt](https://github.com/ekhodzitsky/gigastt) speech-to-text
+server: it runs via ONNX Runtime (no Python at runtime) with the Rust `tokenizers`
+crate, restoring punctuation/casing on the plain `rnnt` head's bare lowercase output, e.g.
+`шестьдесят тысяч тенге сколько будет стоить` → `Шестьдесят тысяч тенге, сколько будет стоить?`.
+
+## Files
+- `rupunct_small_int8.onnx` — dynamic-INT8 graph (DynamicQuantizeLinear + MatMulInteger), ~29 MB.
+- `tokenizer.json`, `config.json`, `special_tokens_map.json`, `tokenizer_config.json` — HF WordPiece tokenizer + label map (33 labels).
+
+## I/O
+- Inputs: `input_ids`, `attention_mask`, `token_type_ids` (int64, `[batch, seq]`).
+- Output: `logits` `[batch, seq, 33]`. Take the first sub-token label per word (aggregation `first`),
+  then apply RUPunct's `process_token` decode (3 case modes × 11 punctuation classes).
+
+## License
+MIT, inherited from the upstream RUPunct/RUPunct_small. Export + INT8 quantization only;
+weights are unchanged in accuracy (fp32 and int8 produce identical labels on test inputs).

config.json

@@ -0,0 +1,96 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "UPPER_PERIOD",
+    "1": "LOWER_PERIOD",
+    "2": "UPPER_TOTAL_PERIOD",
+    "3": "UPPER_COMMA",
+    "4": "LOWER_COMMA",
+    "5": "UPPER_TOTAL_COMMA",
+    "6": "UPPER_QUESTION",
+    "7": "LOWER_QUESTION",
+    "8": "UPPER_TOTAL_QUESTION",
+    "9": "UPPER_TIRE",
+    "10": "LOWER_TIRE",
+    "11": "UPPER_TOTAL_TIRE",
+    "12": "UPPER_VOSKL",
+    "13": "LOWER_VOSKL",
+    "14": "UPPER_TOTAL_VOSKL",
+    "15": "UPPER_DVOETOCHIE",
+    "16": "LOWER_DVOETOCHIE",
+    "17": "UPPER_TOTAL_DVOETOCHIE",
+    "18": "UPPER_PERIODCOMMA",
+    "19": "LOWER_PERIODCOMMA",
+    "20": "UPPER_TOTAL_PERIODCOMMA",
+    "21": "UPPER_DEFIS",
+    "22": "LOWER_DEFIS",
+    "23": "UPPER_TOTAL_DEFIS",
+    "24": "UPPER_QUESTIONVOSKL",
+    "25": "LOWER_QUESTIONVOSKL",
+    "26": "UPPER_TOTAL_QUESTIONVOSKL",
+    "27": "UPPER_MNOGOTOCHIE",
+    "28": "LOWER_MNOGOTOCHIE",
+    "29": "UPPER_TOTAL_MNOGOTOCHIE",
+    "30": "UPPER_O",
+    "31": "LOWER_O",
+    "32": "UPPER_TOTAL_O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "LOWER_COMMA": 4,
+    "LOWER_DEFIS": 22,
+    "LOWER_DVOETOCHIE": 16,
+    "LOWER_MNOGOTOCHIE": 28,
+    "LOWER_O": 31,
+    "LOWER_PERIOD": 1,
+    "LOWER_PERIODCOMMA": 19,
+    "LOWER_QUESTION": 7,
+    "LOWER_QUESTIONVOSKL": 25,
+    "LOWER_TIRE": 10,
+    "LOWER_VOSKL": 13,
+    "UPPER_COMMA": 3,
+    "UPPER_DEFIS": 21,
+    "UPPER_DVOETOCHIE": 15,
+    "UPPER_MNOGOTOCHIE": 27,
+    "UPPER_O": 30,
+    "UPPER_PERIOD": 0,
+    "UPPER_PERIODCOMMA": 18,
+    "UPPER_QUESTION": 6,
+    "UPPER_QUESTIONVOSKL": 24,
+    "UPPER_TIRE": 9,
+    "UPPER_TOTAL_COMMA": 5,
+    "UPPER_TOTAL_DEFIS": 23,
+    "UPPER_TOTAL_DVOETOCHIE": 17,
+    "UPPER_TOTAL_MNOGOTOCHIE": 29,
+    "UPPER_TOTAL_O": 32,
+    "UPPER_TOTAL_PERIOD": 2,
+    "UPPER_TOTAL_PERIODCOMMA": 20,
+    "UPPER_TOTAL_QUESTION": 8,
+    "UPPER_TOTAL_QUESTIONVOSKL": 26,
+    "UPPER_TOTAL_TIRE": 11,
+    "UPPER_TOTAL_VOSKL": 14,
+    "UPPER_VOSKL": 12
+  },
+  "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": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

rupunct_small_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b105da023474d98aa13ba18953ae67b04b17bd0595034bc06030c17536893933
+size 29259673

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 2048,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}