Update app.py

app.py

@@ -2,6 +2,8 @@ import gradio as gr
 from transformers import pipeline, AutoTokenizer
 from huggingsound import SpeechRecognitionModel
 import numpy as np
+import soundfile as sf
+import tempfile
 
 # Load the model for speech recognition
 model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-english")
@@ -16,9 +18,16 @@ def translate_speech(audio_data_tuple):
     # Extract the audio data from the tuple
     sample_rate, audio_data = audio_data_tuple
 
-    # Use the speech recognition model to transcribe the audio
-    output = model.transcribe(audio_data)
-    print(f"Output: {output}")  # Print the output to see what it contains
+    # Save the audio data to a temporary file
+    with tempfile.NamedTemporaryFile(suffix=".wav", delete=True) as temp_audio_file:
+        sf.write(temp_audio_file.name, audio_data, sample_rate)
+
+        # Use the speech recognition model to transcribe the audio
+        output = model.transcribe([temp_audio_file.name])
+        print(f"Output: {output}")  # Print the output to see what it contains
+
+    # ... (rest of your code)
+
 
     # Use the translation pipeline to translate the transcription
     translated_text = translator(output, return_tensors="pt")