Create README.md

README.md

@@ -0,0 +1,31 @@
+---
+language:
+- bn
+metrics:
+- accuracy
+pipeline_tag: audio-classification
+---
+# whisper-tiny-bn-emo
+This model is a fine-tuned version of shhossain/whisper-tiny-bn on the Unknown dataset. It achieves the following results on the evaluation set:
+
+Loss: 0.1842
+Accuracy: 0.9357
+
+## Model Info
+It detects 7 basic human emotions on `Bengali Language`.
+- `ANGRY`
+- `DISGUST`
+- `FEAR`
+- `HAPPY`
+- `NEUTRAL`
+- `SAD`
+- `SURPRISE`
+
+## Usage
+```python
+from transformers import pipeline
+
+pipe = pipeline("audio-classification", model="shhossain/whisper-tiny-bn-emo")
+
+pipe("audio_file.wav")
+```