app1

app.py

@@ -122,24 +122,24 @@ qa_chain = ConversationalRetrievalChain.from_llm(
 import soundfile as sf
 import gradio as gr
 from gradio_client import Client
+import numpy as np
 
 # Load ASR pipeline
-asr_pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large")
+transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-large")
 
 def chat_interface(question, audio_input=None, history=None):
     if audio_input is not None:
         # Function to transcribe the audio input
-        def transcribe_audio(audio):
-            sample_rate, audio_data = audio
-            file_name = "recorded_audio.wav"
-            # Write audio data to a file
-            sf.write(file_name, audio_data, sample_rate)
-            # Transcribe audio using ASR model
-            transcript = asr_pipe(file_name)["text"]
-            return transcript
+
+        def transcribe(audio):
+            sr, y = audio
+            y = y.astype(np.float32)
+            y /= np.max(np.abs(y))
+
+            return transcriber({"sampling_rate": sr, "raw": y})["text"]
 
         # Transcribe the audio input
-        transcribed_text = transcribe_audio(audio_input)
+        transcribed_text = transcribe(audio_input)
 
         # Call the chatbot API with the transcribed text
         client = Client("https://ysharma-explore-llamav2-with-tgi.hf.space/")