Token Classification
Transformers
Safetensors
Finnish
electra
punctuation-restoration
sentence-boundary-detection
truecasing
speech-recognition
streaming
finnish
Instructions to use samuli/mateli-punct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use samuli/mateli-punct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="samuli/mateli-punct")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("samuli/mateli-punct") model = AutoModelForTokenClassification.from_pretrained("samuli/mateli-punct", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from samuli/mateli-punct: direct link, hf CLI and curl.
- Browser
- Download file 1.6 kB
-
https://huggingface.co/samuli/mateli-punct/resolve/main/config.json
- Command line
-
hf download hf://samuli/mateli-punct/config.json
-
curl -L -o config.json https://huggingface.co/samuli/mateli-punct/resolve/main/config.json
1.6 kB
| { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "ElectraForTokenClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": null, | |
| "classifier_dropout": null, | |
| "dtype": "float32", | |
| "embedding_size": 768, | |
| "eos_token_id": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 256, | |
| "id2label": { | |
| "0": "O", | |
| "1": "O|U", | |
| "2": "O|A", | |
| "3": ",", | |
| "4": ",|U", | |
| "5": ",|A", | |
| "6": ".", | |
| "7": ".|U", | |
| "8": ".|A", | |
| "9": "?", | |
| "10": "?|U", | |
| "11": "?|A", | |
| "12": "!", | |
| "13": "!|U", | |
| "14": "!|A" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1024, | |
| "is_decoder": false, | |
| "label2id": { | |
| "!": 12, | |
| "!|A": 14, | |
| "!|U": 13, | |
| ",": 3, | |
| ",|A": 5, | |
| ",|U": 4, | |
| ".": 6, | |
| ".|A": 8, | |
| ".|U": 7, | |
| "?": 9, | |
| "?|A": 11, | |
| "?|U": 10, | |
| "O": 0, | |
| "O|A": 2, | |
| "O|U": 1 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "electra", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "pause_markers": { | |
| "buckets": [ | |
| "[unused1]", | |
| "[unused2]", | |
| "[unused3]", | |
| "[unused4]", | |
| "[unused5]" | |
| ], | |
| "edges": [ | |
| 0.14, | |
| 0.3, | |
| 0.5, | |
| 0.78, | |
| 1.18 | |
| ], | |
| "flag": "[unused0]" | |
| }, | |
| "position_embedding_type": "absolute", | |
| "summary_activation": "gelu", | |
| "summary_last_dropout": 0.1, | |
| "summary_type": "first", | |
| "summary_use_proj": true, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.19.0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 26020 | |
| } |