publish disfluency tagger

README.md

@@ -0,0 +1,27 @@
+---
+license: apache-2.0
+pipeline_tag: token-classification
+tags:
+  - disfluency-detection
+  - transformers.js
+  - onnx
+---
+
+# stillerman/fdt-disfluency-small-29m
+
+Disfluency **deletion tagger** for live speech transcripts: tags every
+whitespace word `KEEP` / `DELETE` / `KEEP_STRIP_COMMA` / `KEEP_CAPITALIZE`,
+then a ~15-line reconstruction turns tags into cleaned text. Deletion-only by
+construction — it cannot rephrase, hallucinate, or alter names and numbers.
+
+- Architecture: BERT L4/H512 (28.5M params), v1 data mix
+- Val metrics: exact-match 0.9325, DELETE-F1 0.9885
+- Training data: synthetic disfluency injection over conversational corpora —
+  see [stillerman/fdt-disfluency-synthetic](https://huggingface.co/datasets/stillerman/fdt-disfluency-synthetic)
+- `onnx/model_quantized.onnx` (int8) is ready for transformers.js
+  (`device: "webgpu"`, `dtype: "q8"`); runs at ~10–50 ms per utterance
+  in-browser.
+- ⚠️ Trained partly on DailyDialog (CC BY-NC-SA): treat as research
+  artifact, not for commercial deployment as-is.
+
+Trained on a DGX Spark as part of the FluencyAI digital-twin project.

config.json

@@ -0,0 +1,40 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "id2label": {
+    "0": "KEEP",
+    "1": "DELETE",
+    "2": "KEEP_STRIP_COMMA",
+    "3": "KEEP_CAPITALIZE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "is_decoder": false,
+  "label2id": {
+    "DELETE": 1,
+    "KEEP": 0,
+    "KEEP_CAPITALIZE": 3,
+    "KEEP_STRIP_COMMA": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.13.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e22e78f915b9a7780bd142af312eb384b81a1b9fc932873e1efced4237e6864
+size 114020336

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4943676614beab903a1221734419004d5f1923988795ed570fe656c30853c14
+size 28725303

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 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

val_metrics.json

@@ -0,0 +1,8 @@
+{
+  "del_p": 0.9825266117694316,
+  "del_r": 0.9945110794877008,
+  "del_f1": 0.9884825217215599,
+  "exact": 0.9325,
+  "epoch": 1,
+  "params_m": 28.503044
+}