Update app.py

app.py

@@ -4,7 +4,7 @@ import soundfile as sf
 import numpy as np
 import tempfile
 from pydub import AudioSegment
-import io  # Add this line
+import io
 
 # Define the Hugging Face Inference API URLs and headers
 ASR_API_URL = "https://api-inference.huggingface.co/models/Baghdad99/saad-speech-recognition-hausa-audio-to-text"
@@ -29,8 +29,13 @@ def translate_speech(audio):
         sf.write(f, audio_data, sample_rate)
         audio_file = f.name
 
+    # Convert the WAV file to MP3
+    audio_segment = AudioSegment.from_wav(audio_file)
+    mp3_file = audio_file.replace(".wav", ".mp3")
+    audio_segment.export(mp3_file, format="mp3")
+
     # Use the ASR pipeline to transcribe the audio
-    with open(audio_file, "rb") as f:
+    with open(mp3_file, "rb") as f:  # Change this line
         data = f.read()
     response = requests.post(ASR_API_URL, headers=headers, data=data)
     output = response.json()
@@ -50,8 +55,7 @@ def translate_speech(audio):
     audio_bytes = response.content
 
     # Convert the audio bytes to an audio segment
-    audio_segment = AudioSegment.from_mp3(io.BytesIO(audio_bytes))
-
+    audio_segment = AudioSegment.from_mp3(io.BytesIO(audio_bytes))  # Change this line
 
     # Convert the audio segment to a numpy array
     audio_data = np.array(audio_segment.get_array_of_samples())