Update app.py

app.py

@@ -8,7 +8,11 @@ import json
 from scipy.io import wavfile
 from pydub import AudioSegment
 import gradio as gr
+import io
+from io import BytesIO
+import soundfile as sf
 
+# Load the model
 model = hub.load('Audio_Multiple_v1')
 
 def class_names_from_csv(class_map_csv_text):
@@ -29,76 +33,84 @@ def ensure_sample_rate(original_sample_rate, waveform, desired_sample_rate=16000
         waveform = scipy.signal.resample(waveform, desired_length)
     return desired_sample_rate, waveform
 
-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):
-    sample_rate, wav_data = wavfile.read(file_path, 'rb')
-    if wav_data.ndim > 1:  # Convert stereo to mono if needed
+def convert_mp3_to_wav(mp3_data):
+    audio = AudioSegment.from_file(io.BytesIO(mp3_data), format="mp3")
+    wav_buffer = io.BytesIO()
+    audio.export(wav_buffer, format='wav')
+    wav_buffer.seek(0)
+    return wav_buffer
+
+def process_audio_file(file_data, url):
+    sample_rate, wav_data = wavfile.read(BytesIO(file_data))      
+    
+    if wav_data.ndim > 1:                        
         wav_data = np.mean(wav_data, axis=1)
     sample_rate, wav_data = ensure_sample_rate(sample_rate, wav_data)
 
     waveform = wav_data / tf.int16.max
-    waveform = tf.convert_to_tensor(waveform, dtype=tf.float32)
 
-    scores, embeddings, spectrogram = model(waveform)
+    scores, embeddings, spectrogram = model(waveform)      
 
     scores_np = scores.numpy()
     mean_scores = np.mean(scores, axis=0)
 
-    inferred_class = class_names[mean_scores.argmax()]
-
-    confidence_threshold = 0.60
+    inferred_class = class_names[mean_scores.argmax()]    
+    
+    confidence_threshold = 0.60                 
     confident_classes = set()
 
-    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:
                 class_name = class_names[i]
 
-                if class_name == 'Child speech, kid speaking':
-                    class_name = 'Child speech'
-                elif class_name == 'Vehicle horn, car horn, honking':
-                    class_name = 'Vehicle horn'
-                elif class_name == 'Railroad car, train wagon':
-                    class_name = 'Train/wagon'
-                elif class_name == 'Rail transport':
-                    class_name = 'Train/wagon'
+                if class_name =='Child speech, kid speaking':
+                    class_name='Child speech'
+                elif class_name =='Vehicle horn, car horn, honking':
+                    class_name='Vehicle horn'
+                elif class_name =='Railroad car, train wagon':
+                    class_name='Train/wagon'
+                elif class_name=='Rail transport':
+                    class_name='Train/wagon'
 
                 if class_name not in exclusion_list:
                     confident_classes.add(class_name)
 
-    confident_classes = sorted(confident_classes)
+    confident_classes = sorted(confident_classes)        
+    
+    answer_dict= {}  
+    answer_dict.update({'file_name': url, 'class_names': confident_classes})  #os.path.basename(file_path
+    solutions.append(answer_dict)
 
-    return confident_classes
+def get_audio_data(url):
+    response = requests.get(url)
+    response.raise_for_status()
+    return response.content
 
 def process_audio(params):
-    # try
-    params = json.loads(params)
-    # except json.JSONDecodeError:
-        # return {"error": "Invalid JSON input"}
+    try:
+        params = json.loads(params)
+    except json.JSONDecodeError as e:
+        return {"error": f"Invalid JSON input: {e.msg} at line {e.lineno} column {e.colno}"}
 
     audio_files = params.get("audio_files", [])
     api = params.get("api", "")
     job_id = params.get("job_id", "")
 
     solutions = []
-    for audio in audio_files:
-        if audio.endswith(".mp3"):
-            wav_file_path = convert_mp3_to_wav(audio)
-            class_names = process_audio_file(wav_file_path)
-        elif audio.endswith(".wav"):
-            class_names = process_audio_file(audio)
-        
-        answer_dict = {'file_name': audio, 'class_names': class_names}
-        solutions.append(answer_dict)
+    for audio_url in audio_files:
+        audio_data = get_audio_data(audio_url)
+
+        if audio_url.endswith(".mp3"):            
+            wav_buffer = convert_mp3_to_wav(audio_data)
+            process_audio_file(wav_buffer.getvalue(), audio_url)
+
+        elif audio_url.endswith(".wav"):           
+            process_audio_file(audio_data, audio_url)
 
     result_url = f"{api}/{job_id}"
-    # send_results_to_api(solutions, result_url)
+    response = requests.patch(result_url, json={"solutions": solutions})
 
     return json.dumps({"solutions": solutions}, indent=4)
 
@@ -114,4 +126,4 @@ inputt = gr.Textbox(label="Parameters (JSON format) Eg. {'audio_files':['file1.m
 outputs = gr.JSON()
 
 application = gr.Interface(fn=process_audio, inputs=inputt, outputs=outputs, title="Audio Classification with API Integration")
-application.launch()
+application.launch()