first model, trained from Welsh Parliament/Senedd hansard

.gitattributes

@@ -30,3 +30,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,32 @@
 ---
+language:
+ - cy
+tags:
+ - punctuation prediction
+ - punctuation
 license: mit
+widget:
+ - text: "a yw'r gweinidog yn cytuno bod angen gwell gwasanaethau yn ne dwyrain cymru"
+   example_title: "Example 1"
+ - text: "mae pwllheli yn dref yn gwynedd gogledd cymru ac mae llandrindod ym mhowys"
+   example_title: "Example 2"
+metrics:
+ - f1
+
+## Results
+
+
+| Label         | Precision    | Recall    | f1-score    | Support    |
+| ------------- | ----- | ----- | ----- | ----- |
+| 0             | 0.99  | 0.99  | 0.99  | 5053572    |
+| .             | 0.89  | 0.88  | 0.88  | 224920     |
+| ,             | 0.83  | 0.82  | 0.82  | 363886     |
+| ?             | 0.91  | 0.87  | 0.89  | 20762      |
+| -             | 0.95  | 0.94  | 0.94  | 13161      |
+| :             | 0.92  | 0.89  | 0.90  | 5274       |
+|                  |      |      |      |          |
+| accuracy         |      |      | 0.98 | 11012581 |
+| macro average    | 0.92 | 0.90 | 0.91 | 11012581 |
+| weighted average | 0.98 | 0.98 | 0.98 | 11012581 |
+
 ---

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e822b3fca11cbb329f3dd7714e9112e5b0f0c81c5e9a9822e2b1723e773acc28
+size 2235524465

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>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
+size 17082758

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_prefix_space": true,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "xlm-roberta-large",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "strip_accent": false,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb87f568d0ad43eded222ce946cb43af506e51d22b520c14b13a681be169babd
+size 3439