Instructions to use Talha/urdu-audio-emotions with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Talha/urdu-audio-emotions with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="Talha/urdu-audio-emotions")# Load model directly from transformers import AutoProcessor, AutoModelForAudioClassification processor = AutoProcessor.from_pretrained("Talha/urdu-audio-emotions") model = AutoModelForAudioClassification.from_pretrained("Talha/urdu-audio-emotions", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,18 +20,19 @@ It achieves the following results on the evaluation set:
|
|
| 20 |
- Accuracy: 0.975
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
More information needed
|
| 29 |
|
| 30 |
## Training and evaluation data
|
| 31 |
-
|
| 32 |
-
|
| 33 |
|
| 34 |
## Training procedure
|
|
|
|
|
|
|
| 35 |
|
| 36 |
### Training hyperparameters
|
| 37 |
|
|
|
|
| 20 |
- Accuracy: 0.975
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
+
The model Urdu audio and classify in following categories
|
| 24 |
+
* Angry
|
| 25 |
+
* Happy
|
| 26 |
+
* Neutral
|
| 27 |
+
* Sad
|
|
|
|
| 28 |
|
| 29 |
## Training and evaluation data
|
| 30 |
+
The dataset is available at
|
| 31 |
+
https://www.kaggle.com/datasets/kingabzpro/urdu-emotion-dataset
|
| 32 |
|
| 33 |
## Training procedure
|
| 34 |
+
Training code is available at
|
| 35 |
+
https://www.kaggle.com/code/chtalhaanwar/urdu-emotions-hf
|
| 36 |
|
| 37 |
### Training hyperparameters
|
| 38 |
|