Update app.py

app.py

@@ -1,17 +1,39 @@
 import time
 import random
+import whisper
 import gradio as gr
 from transformers import pipeline
 
-p = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
+transcription_model = whisper.load_model("small")
+
+def transcribe(audio):
+    
+    # time.sleep(3)
+    # load audio and pad/trim it to fit 30 seconds
+    audio = whisper.load_audio(audio)
+    audio = whisper.pad_or_trim(audio)
+
+    # make log-Mel spectrogram and move to the same device as the transcription_model
+    mel = whisper.log_mel_spectrogram(audio).to(transcription_model.device)
+
+    # detect the spoken language
+    _, probs = transcription_model.detect_language(mel)
+    # print(f"Detected language: {max(probs, key=probs.get)}")
+
+    # decode the audio
+    options = whisper.DecodingOptions(fp16 = False)
+    result = whisper.decode(transcription_model, mel, options)
+    return result.text
+
+# p = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
+
+# def transcribe(audio):
+#     text = p(audio)["text"]
+#     return text
 
 def user(user_message, history):
     return "", history + [[user_message, None]]
 
-def transcribe(audio):
-    text = p(audio)["text"]
-    return text
-
 def bot(history):
     bot_message = random.choice(["How are you?", "I wanted to tell you that...", "hehehe", "huihuihuihui", "I'm very hungry"])
     history[-1][1] = ""