Upload 7 files
Browse files- README.md +109 -3
- config.json +27 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- vocab.txt +0 -0
README.md
CHANGED
|
@@ -1,3 +1,109 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: es
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
tags:
|
| 5 |
+
- spanish
|
| 6 |
+
- hate-speech-detection
|
| 7 |
+
- text-classification
|
| 8 |
+
- beto
|
| 9 |
+
- inclusivity
|
| 10 |
+
datasets:
|
| 11 |
+
- manueltonneau/spanish-hate-speech-superset
|
| 12 |
+
metrics:
|
| 13 |
+
- accuracy
|
| 14 |
+
- f1
|
| 15 |
+
- precision
|
| 16 |
+
- recall
|
| 17 |
+
widget:
|
| 18 |
+
- text: "Me encanta este país, la gente es muy amable"
|
| 19 |
+
- text: "Todos los inmigrantes son delincuentes"
|
| 20 |
+
---
|
| 21 |
+
|
| 22 |
+
# InclusioCheck - Detector de Lenguaje de Odio en Español
|
| 23 |
+
|
| 24 |
+
## 📋 Descripción del Modelo
|
| 25 |
+
|
| 26 |
+
**InclusioCheck** es un modelo de clasificación de texto fine-tuned desde [BETO](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased)
|
| 27 |
+
para detectar lenguaje de odio (hate speech) en textos en español.
|
| 28 |
+
|
| 29 |
+
## 🚀 Uso Rápido
|
| 30 |
+
|
| 31 |
+
```python
|
| 32 |
+
from transformers import pipeline
|
| 33 |
+
|
| 34 |
+
# Cargar el clasificador
|
| 35 |
+
classifier = pipeline("text-classification", model="antonn-dromundo/InclusioCheck-BETO-HateSpeech")
|
| 36 |
+
|
| 37 |
+
# Predecir
|
| 38 |
+
resultado = classifier("Texto a analizar")
|
| 39 |
+
print(resultado)
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
+
## 💻 Uso Avanzado
|
| 43 |
+
|
| 44 |
+
```python
|
| 45 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 46 |
+
import torch
|
| 47 |
+
|
| 48 |
+
# Cargar modelo y tokenizer
|
| 49 |
+
tokenizer = AutoTokenizer.from_pretrained("antonn-dromundo/InclusioCheck-BETO-HateSpeech")
|
| 50 |
+
model = AutoModelForSequenceClassification.from_pretrained("antonn-dromundo/InclusioCheck-BETO-HateSpeech")
|
| 51 |
+
|
| 52 |
+
# Función de predicción
|
| 53 |
+
def predecir(texto):
|
| 54 |
+
inputs = tokenizer(texto, return_tensors="pt", truncation=True, max_length=128)
|
| 55 |
+
with torch.no_grad():
|
| 56 |
+
outputs = model(**inputs)
|
| 57 |
+
prediccion = outputs.logits.argmax(-1).item()
|
| 58 |
+
probabilidad = torch.softmax(outputs.logits, dim=-1)[0][prediccion].item()
|
| 59 |
+
|
| 60 |
+
label = "Hate Speech" if prediccion == 1 else "No Hate Speech"
|
| 61 |
+
return {"label": label, "confidence": probabilidad}
|
| 62 |
+
|
| 63 |
+
# Ejemplo
|
| 64 |
+
print(predecir("Los inmigrantes son bienvenidos"))
|
| 65 |
+
```
|
| 66 |
+
|
| 67 |
+
## 📊 Métricas de Rendimiento
|
| 68 |
+
|
| 69 |
+
| Métrica | Valor |
|
| 70 |
+
|---------|-------|
|
| 71 |
+
| Accuracy | 0.816 |
|
| 72 |
+
| F1 Score | 0.827 |
|
| 73 |
+
| Precision | 0.777 |
|
| 74 |
+
| Recall | 0.884 |
|
| 75 |
+
|
| 76 |
+
## 📚 Dataset de Entrenamiento
|
| 77 |
+
|
| 78 |
+
- **Fuente**: [Spanish Hate Speech Superset](https://huggingface.co/datasets/manueltonneau/spanish-hate-speech-superset)
|
| 79 |
+
- **Ejemplos de entrenamiento**: 12,350
|
| 80 |
+
- **Ejemplos de test**: 2,180
|
| 81 |
+
- **Clases**: 2 (No Hate / Hate Speech)
|
| 82 |
+
- **Balanceo**: Sí (undersampling de clase mayoritaria)
|
| 83 |
+
|
| 84 |
+
## 🎯 Casos de Uso
|
| 85 |
+
|
| 86 |
+
- ✅ Moderación automática de contenido
|
| 87 |
+
- ✅ Filtrado de comentarios en redes sociales
|
| 88 |
+
- ✅ Auditoría de lenguaje inclusivo
|
| 89 |
+
- ✅ Herramienta de apoyo para redacción
|
| 90 |
+
|
| 91 |
+
## ⚠️ Limitaciones
|
| 92 |
+
|
| 93 |
+
- El modelo está entrenado específicamente para **español**
|
| 94 |
+
- Puede tener sesgos inherentes al dataset de entrenamiento
|
| 95 |
+
- Recomendado como **herramienta de apoyo**, no como única fuente de decisión
|
| 96 |
+
- El contexto cultural y la intención deben considerarse en casos ambiguos
|
| 97 |
+
|
| 98 |
+
## 👤 Autoría
|
| 99 |
+
Antonio Dromundo
|
| 100 |
+
Creado como parte del proyecto **InclusioCheck** para promover la detección de lenguaje excluyente.
|
| 101 |
+
De Mexico para el mundo
|
| 102 |
+
## 📄 Licencia
|
| 103 |
+
|
| 104 |
+
Apache 2.0
|
| 105 |
+
|
| 106 |
+
## 🔗 Enlaces
|
| 107 |
+
|
| 108 |
+
- [Repositorio del proyecto](#)
|
| 109 |
+
- [Demo en Gradio](#)
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"output_past": true,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"problem_type": "single_label_classification",
|
| 23 |
+
"transformers_version": "4.57.1",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 31002
|
| 27 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1ba5f2e2fdc9aea23c4ba2ef5f39977e3aa93eb5e911ba717b7408b7d267bab
|
| 3 |
+
size 439433208
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[MASK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"3": {
|
| 20 |
+
"content": "[UNK]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"4": {
|
| 28 |
+
"content": "[CLS]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"5": {
|
| 36 |
+
"content": "[SEP]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": false,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|