Update README.md
Browse files
README.md
CHANGED
@@ -54,22 +54,15 @@ inference:
|
|
54 |
temperature: 1
|
55 |
---
|
56 |
|
57 |
-
"Chinese (中文)", "Spanish (Español)", "Hindi (हिन्दी)", "Arabic (العربية)",
|
58 |
-
"Bengali (বাংলা)", "Portuguese (Português)", "Russian (Русский)", "Japanese (日本語)",
|
59 |
-
"German (Deutsch)", "Malay (Bahasa Melayu)", "Telugu (తెలుగు)",
|
60 |
-
"Vietnamese (Tiếng Việt)", "Korean (한국어)", "French (Français)", "Turkish (Türkçe)",
|
61 |
-
"Italian (Italiano)", "Polish (Polski)", "Ukrainian (Українська)",
|
62 |
-
"Tagalog", "Dutch (Nederlands)", "Swiss German (Schweizerdeutsch)"
|
63 |
|
64 |
# 🚀 distilbert-based Multilingual Sentiment Classification Model
|
65 |
|
66 |
-
TRY IT HERE:
|
67 |
|
68 |
|
69 |
# NEWS!
|
70 |
|
71 |
- 2024/12: We are excited to introduce a multilingual sentiment model! Now you can analyze sentiment across multiple languages, enhancing your global reach.
|
72 |
-
```
|
73 |
|
74 |
## Model Details
|
75 |
- `Model Name:` tabularisai/multilingual-sentiment-analysis
|
@@ -111,7 +104,7 @@ Ideal for:
|
|
111 |
|
112 |
Below is a Python example on how to use the multilingual sentiment model:
|
113 |
|
114 |
-
```
|
115 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
116 |
import torch
|
117 |
|
@@ -160,26 +153,6 @@ for text in texts:
|
|
160 |
print(f"Sentiment: {sentiment}\n")
|
161 |
```
|
162 |
|
163 |
-
## Model Performance
|
164 |
-
|
165 |
-
Example predictions:
|
166 |
-
|
167 |
-
$$$
|
168 |
-
1. "I absolutely loved this movie! The acting was superb and the plot was engaging."
|
169 |
-
Predicted Sentiment: Very Positive (English)
|
170 |
-
|
171 |
-
2. "我讨厌这种无休止的争吵。"
|
172 |
-
Predicted Sentiment: Very Negative (Chinese)
|
173 |
-
|
174 |
-
3. "El producto funciona como se espera. Nada especial, pero cumple con su función."
|
175 |
-
Predicted Sentiment: Neutral (Spanish)
|
176 |
-
|
177 |
-
4. "هذا الكتاب غير حياتي! لقد تعلمت الكثير منه."
|
178 |
-
Predicted Sentiment: Very Positive (Arabic)
|
179 |
-
|
180 |
-
5. "Я разочарован покупкой, это не так хорошо, как я надеялся."
|
181 |
-
Predicted Sentiment: Negative (Russian)
|
182 |
-
$$$
|
183 |
|
184 |
## Training Procedure
|
185 |
|
@@ -199,6 +172,6 @@ Will be included.
|
|
199 |
|
200 |
## Contact
|
201 |
|
202 |
-
For inquiries
|
203 |
|
204 |
tabularis.ai
|
|
|
54 |
temperature: 1
|
55 |
---
|
56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
|
58 |
# 🚀 distilbert-based Multilingual Sentiment Classification Model
|
59 |
|
60 |
+
TRY IT HERE: `coming soon`
|
61 |
|
62 |
|
63 |
# NEWS!
|
64 |
|
65 |
- 2024/12: We are excited to introduce a multilingual sentiment model! Now you can analyze sentiment across multiple languages, enhancing your global reach.
|
|
|
66 |
|
67 |
## Model Details
|
68 |
- `Model Name:` tabularisai/multilingual-sentiment-analysis
|
|
|
104 |
|
105 |
Below is a Python example on how to use the multilingual sentiment model:
|
106 |
|
107 |
+
```python
|
108 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
109 |
import torch
|
110 |
|
|
|
153 |
print(f"Sentiment: {sentiment}\n")
|
154 |
```
|
155 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
156 |
|
157 |
## Training Procedure
|
158 |
|
|
|
172 |
|
173 |
## Contact
|
174 |
|
175 |
+
For inquiries, private APIs, better models, contact info@tabularis.ai
|
176 |
|
177 |
tabularis.ai
|