Upload folder using huggingface_hub

best_emotion_model.keras

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68d8fa64acc6706167a86c7fc177ee1bdd7df5d6e7a34978471ee7283f35101f
-size 8129142
+oid sha256:045c6926ad8a2db4300f046b277bc3d45f5d1f9569638fd242503c40fcacdeab
+size 11589719

emotion_recognition_model.keras

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7712b825c0c090d75fb0e3c2885b725e660075d32f247ac1cc864c2a397290f3
-size 8129142
+oid sha256:17d42eb5c16319510b808d7a2219d19d3adc62b6259597ab811564a02f13f08a
+size 11589719

emotion_recognition_wrapper_model.keras

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5dd2ebde36afbbd3aa5e98d2baa0201d443b15d1dc1c342aaea8f5ab9586c79
-size 8117654
+oid sha256:81885670209be184409345406394306fe3f3743a1f5dda0bf52d92e1a7ecd7b9
+size 11574306

example_usage.py

@@ -9,18 +9,18 @@ def load_model(model_path):
     "Load the emotion recognition model."
     return tf.keras.models.load_model(model_path)
 
-def predict_emotion(model, audio_path, preprocessing_config):
+def predict_emotion(model, audio_path, preprocessor_config):
     "Predict emotion from an audio file."
     # Load audio file
     waveform, sr = librosa.load(
         audio_path, 
-        sr=preprocessing_config["sample_rate"],
-        duration=preprocessing_config["duration"],
-        offset=preprocessing_config["offset"]
+        sr=preprocessor_config["sample_rate"],
+        duration=preprocessor_config["duration"],
+        offset=preprocessor_config["offset"]
     )
     
     # Ensure consistent length
-    target_length = int(preprocessing_config["sample_rate"] * preprocessing_config["duration"])
+    target_length = int(preprocessor_config["sample_rate"] * preprocessor_config["duration"])
     if len(waveform) < target_length:
         waveform = np.pad(waveform, (0, target_length - len(waveform)))
     if len(waveform) > target_length:
@@ -29,9 +29,9 @@ def predict_emotion(model, audio_path, preprocessing_config):
     # Extract features
     mel_spec = librosa.feature.melspectrogram(
         y=waveform,
-        sr=preprocessing_config["sample_rate"],
-        n_fft=preprocessing_config["frame_length"],
-        hop_length=preprocessing_config["hop_length"],
+        sr=preprocessor_config["sample_rate"],
+        n_fft=preprocessor_config["frame_length"],
+        hop_length=preprocessor_config["hop_length"],
         n_mels=128
     )
     
@@ -46,7 +46,7 @@ def predict_emotion(model, audio_path, preprocessing_config):
     
     # Get emotion label
     emotion_idx = np.argmax(prediction)
-    emotion = preprocessing_config["emotions"][str(emotion_idx)]
+    emotion = preprocessor_config["emotions"][str(emotion_idx)]
     
     return emotion, prediction[emotion_idx]
 
@@ -55,14 +55,14 @@ if __name__ == "__main__":
     # Load model
     model = load_model("emotion_recognition_model.keras")
     
-    # Load preprocessing config
+    # Load preprocessor_config
     with open("preprocessing.json", "r") as f:
-        preprocessing_config = json.load(f)
+        preprocessor_config = json.load(f)
     
     # Path to your audio file
     audio_path = "path/to/your/audio.wav"
     
     # Predict emotion
-    emotion, confidence = predict_emotion(model, audio_path, preprocessing_config)
+    emotion, confidence = predict_emotion(model, audio_path, preprocessor_config)
     
     print(f"Predicted emotion: {emotion} with confidence {confidence:.2f}")