Update app.py

app.py

@@ -9,9 +9,9 @@ from scipy.io import wavfile
 from pydub import AudioSegment
 import gradio as gr
 
-model = hub.load('Audio_Multiple_v1')       #loading model
+model = hub.load('D:\\Databae\\Saved Models\\FINAL MODELS\\Audio Multiple\\Audio_Multiple_v1')
 
-def class_names_from_csv(class_map_csv_text):            # Function to load class names from CSV.
+def class_names_from_csv(class_map_csv_text):
     """Returns list of class names corresponding to score vector."""
     class_names = []
     with tf.io.gfile.GFile(class_map_csv_text) as csvfile:
@@ -23,19 +23,19 @@ def class_names_from_csv(class_map_csv_text):            # Function to load clas
 class_map_path = model.class_map_path().numpy()
 class_names = class_names_from_csv(class_map_path)
 
-def ensure_sample_rate(original_sample_rate, waveform, desired_sample_rate=16000):   #to ensure/make a standard sample rate for audio
+def ensure_sample_rate(original_sample_rate, waveform, desired_sample_rate=16000):
     if original_sample_rate != desired_sample_rate:  # Resample waveform if required
         desired_length = int(round(float(len(waveform)) / original_sample_rate * desired_sample_rate))
         waveform = scipy.signal.resample(waveform, desired_length)
     return desired_sample_rate, waveform
 
-def convert_mp3_to_wav(mp3_file_path):        #if audio file is mp3 then convert it to wav
+def convert_mp3_to_wav(mp3_file_path):
     audio = AudioSegment.from_mp3(mp3_file_path)
     wav_file_path = mp3_file_path.replace('.mp3', '.wav')
     audio.export(wav_file_path, format='wav')
     return wav_file_path
 
-def process_audio_file(file_path):          #reading audio file and making stereo to mono
+def process_audio_file(file_path):
     sample_rate, wav_data = wavfile.read(file_path, 'rb')
     if wav_data.ndim > 1:  # Convert stereo to mono if needed
         wav_data = np.mean(wav_data, axis=1)
@@ -54,8 +54,7 @@ def process_audio_file(file_path):          #reading audio file and making stere
     confidence_threshold = 0.60
     confident_classes = set()
 
-    #excluding some unwanted classes
-    exclusion_list = ['Mechanisms','Domestic animals, pets', 'Animal', 'Silence', 'Alarm', 'Wind chime', 'Water', 'Livestock, farm animals, working animals', 'Wild animals', 'Bleat', 'Siren', 'Computer keyboard', 'Toot', 'Shatter', 'Bird','Caw', 'Independent music', 'Tender music', 'Ocean', 'House music', 'Middle Eastern music', 'Swing music', 'Soul music', 'Shofar', 'Motor vehicle (road)', 'White noise','Pink noise', 'Cacophony', 'Sidetone', 'Static', 'Outside, rural or natural', 'Outside, urban or manmade', 'Inside, public space', 'Inside, large room or hall', 'Inside, small room', 'Sound effect'  ]
+    exclusion_list = ['Mechanisms','Domestic animals, pets', 'Animal', 'Silence', 'Alarm', 'Wind chime', 'Water', 'Livestock, farm animals, working animals', 'Wild animals', 'Bleat', 'Siren', 'Computer keyboard', 'Toot', 'Shatter', 'Bird','Caw', 'Independent music', 'Tender music', 'Ocean', 'House music', 'Middle Eastern music', 'Swing music', 'Soul music', 'Shofar', 'Motor vehicle (road)', 'White noise','Pink noise', 'Cacophony', 'Sidetone', 'Static', 'Outside, rural or natural', 'Outside, urban or manmade', 'Inside, public space', 'Inside, large room or hall', 'Inside, small room', 'Sound effect']
     for frame_scores in scores_np:
         for i, score in enumerate(frame_scores):
             if score > confidence_threshold:
@@ -74,9 +73,9 @@ def process_audio_file(file_path):          #reading audio file and making stere
                     confident_classes.add(class_name)
 
     confident_classes = sorted(confident_classes)
+
     return confident_classes
 
-#main function to get the input
 def process_audio(params):
     try:
         params = json.loads(params)
@@ -99,7 +98,6 @@ def process_audio(params):
         solutions.append(answer_dict)
 
     result_url = f"{api}/{job_id}"
-    
     # send_results_to_api(solutions, result_url)
 
     return json.dumps({"solutions": solutions}, indent=4)
@@ -112,8 +110,8 @@ def send_results_to_api(data, result_url):
     else:
         return {"error": f"Failed to send results to API: {response.status_code}"}
 
-inputt = gr.Textbox(label="Parameters (JSON format) Eg. audio_files:['',''], api:'', job_id:''")
-outputts = gr.JSON()
+inputt = gr.Textbox(label="Parameters (JSON format) Eg. {'audio_files':['file1.mp3','file2.wav'], 'api':'https://api.example.com', 'job_id':'12345'}")
+outputs = gr.JSON()
 
-application = gr.Interface(fn=process_audio, inputs=inputt, outputs=outputts, title="Audio Classification with API Integration")
-application.launch()
+application = gr.Interface(fn=process_audio, inputs=inputt, outputs=outputs, title="Audio Classification with API Integration")
+application.launch()