save

app.py

@@ -44,27 +44,27 @@ def runApi():
     audio = "audio.mp3"
 
     audioOri = whisper.load_audio(audio)
-    audio = whisper.pad_or_trim(audioOri)
+    # audio = whisper.pad_or_trim(audioOri)
     
-    mel = whisper.log_mel_spectrogram(audio).to(model.device)
+    # mel = whisper.log_mel_spectrogram(audio).to(model.device)
     
-    _, probs = model.detect_language(mel)
+    # _, probs = model.detect_language(mel)
     
-    options = whisper.DecodingOptions(fp16 = False)
-    result = whisper.decode(model, mel, options)
+    # options = whisper.DecodingOptions(fp16 = False)
+    # result = whisper.decode(model, mel, options)
 
     # test 2
     # ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
     # sample = ds[0]["audio"]
     prediction = pipe(audioOri)["text"]
-    print(prediction)
+  
 
     end_time = time.time()
     total_time = end_time - start_time
 
     return jsonify({
         "audio_url": audio_url,
-        "result": result.text,
+        "result": prediction,
         "exec_time_sec": total_time
     })