roushan
#5
by roushankr242 - opened
README.md
CHANGED
|
@@ -45,14 +45,6 @@ datasets:
|
|
| 45 |
- tabularisai/swahili_sentiment_dataset
|
| 46 |
---
|
| 47 |
|
| 48 |
-
> [!TIP]
|
| 49 |
-
> 🚀 These models are now available through the Tabularis API.
|
| 50 |
-
> Fast multilingual sentiment + emotion classification in 23 languages with structured outputs and simple pricing.
|
| 51 |
-
>
|
| 52 |
-
> ✅ Free 10K credits/month
|
| 53 |
-
> 📚 Docs + API key: https://tabularis.ai/sentiment-analysis/
|
| 54 |
-
|
| 55 |
-
|
| 56 |
|
| 57 |
# 🚀 Multilingual Sentiment Classification Model (23 Languages)
|
| 58 |
|
|
@@ -64,15 +56,17 @@ datasets:
|
|
| 64 |
# NEWS!
|
| 65 |
- 2025/8: Major model update +1 new language: **Swahili**! Also, general improvements accross all languages.
|
| 66 |
|
| 67 |
-
- 2025/8: Free
|
| 68 |
|
| 69 |
- 2025/7: We’ve just released ModernFinBERT, a model we’ve been working on for a while. It’s built on the ModernBERT architecture and trained on a mix of real and synthetic data, with LLM-based label correction applied to public datasets to fix human annotation errors.
|
| 70 |
It’s performing well across a range of benchmarks — in some cases improving accuracy by up to 48% over existing models like FinBERT.
|
| 71 |
You can check it out here on Hugging Face:
|
| 72 |
👉 https://huggingface.co/tabularisai/ModernFinBERT
|
| 73 |
|
|
|
|
|
|
|
| 74 |
|
| 75 |
-
## 🔌 Hosted
|
| 76 |
|
| 77 |
We provide a hosted inference API:
|
| 78 |
|
|
@@ -100,6 +94,7 @@ curl -X POST https://api.tabularis.ai/ \
|
|
| 100 |
- Customer service optimization
|
| 101 |
- Competitive intelligence
|
| 102 |
|
|
|
|
| 103 |
|
| 104 |
|
| 105 |
## Model Description
|
|
@@ -212,14 +207,13 @@ Synthetic data reduces bias, but validation in real-world scenarios is advised.
|
|
| 212 |
|
| 213 |
## Citation
|
| 214 |
```bib
|
| 215 |
-
@misc{
|
| 216 |
-
|
| 217 |
-
|
| 218 |
-
|
| 219 |
-
|
| 220 |
-
|
| 221 |
-
|
| 222 |
-
note = {Revision 69afb83}
|
| 223 |
}
|
| 224 |
```
|
| 225 |
|
|
|
|
| 45 |
- tabularisai/swahili_sentiment_dataset
|
| 46 |
---
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
|
| 49 |
# 🚀 Multilingual Sentiment Classification Model (23 Languages)
|
| 50 |
|
|
|
|
| 56 |
# NEWS!
|
| 57 |
- 2025/8: Major model update +1 new language: **Swahili**! Also, general improvements accross all languages.
|
| 58 |
|
| 59 |
+
- 2025/8: Free API for our model! Please see below!
|
| 60 |
|
| 61 |
- 2025/7: We’ve just released ModernFinBERT, a model we’ve been working on for a while. It’s built on the ModernBERT architecture and trained on a mix of real and synthetic data, with LLM-based label correction applied to public datasets to fix human annotation errors.
|
| 62 |
It’s performing well across a range of benchmarks — in some cases improving accuracy by up to 48% over existing models like FinBERT.
|
| 63 |
You can check it out here on Hugging Face:
|
| 64 |
👉 https://huggingface.co/tabularisai/ModernFinBERT
|
| 65 |
|
| 66 |
+
- 2024/12: We are excited to introduce a multilingual sentiment model! Now you can analyze sentiment across multiple languages, enhancing your global reach.
|
| 67 |
+
|
| 68 |
|
| 69 |
+
## 🔌 Hosted API
|
| 70 |
|
| 71 |
We provide a hosted inference API:
|
| 72 |
|
|
|
|
| 94 |
- Customer service optimization
|
| 95 |
- Competitive intelligence
|
| 96 |
|
| 97 |
+
> If you wish to use this model for commercial purposes, please obtain a license by contacting: info@tabularis.ai
|
| 98 |
|
| 99 |
|
| 100 |
## Model Description
|
|
|
|
| 207 |
|
| 208 |
## Citation
|
| 209 |
```bib
|
| 210 |
+
@misc{tabularisai_2025,
|
| 211 |
+
author = { tabularisai and Samuel Gyamfi and Vadim Borisov and Richard H. Schreiber },
|
| 212 |
+
title = { multilingual-sentiment-analysis (Revision 69afb83) },
|
| 213 |
+
year = 2025,
|
| 214 |
+
url = { https://huggingface.co/tabularisai/multilingual-sentiment-analysis },
|
| 215 |
+
doi = { 10.57967/hf/5968 },
|
| 216 |
+
publisher = { Hugging Face }
|
|
|
|
| 217 |
}
|
| 218 |
```
|
| 219 |
|