Update app.py

app.py

@@ -5,24 +5,28 @@ from pydub import AudioSegment
 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"
 TTS_API_URL = "https://api-inference.huggingface.co/models/Baghdad99/english_voice_tts"
 TRANSLATION_API_URL = "https://api-inference.huggingface.co/models/Baghdad99/saad-hausa-text-to-english-text"
 headers = {"Authorization": "Bearer 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"}
 
-# Load the Gradio model for speech recognition
-asr_model = gr.load("models/Baghdad99/saad-speech-recognition-hausa-audio-to-text")
-
 # Define the function to query the Hugging Face Inference API
-def query(api_url, payload):
-    response = requests.post(api_url, headers=headers, json=payload)
+def query(api_url, payload=None, data=None):
+    if data is not None:
+        response = requests.post(api_url, headers=headers, data=data)
+    else:
+        response = requests.post(api_url, headers=headers, json=payload)
     return response.json()
 
 # Define the function to translate speech
 def translate_speech(audio_file):
     print(f"Type of audio: {type(audio_file)}, Value of audio: {audio_file}")  # Debug line
 
-    # Use the ASR model to transcribe the audio
-    transcription = asr_model.predict(audio_file.name)  # Change this line
+    # Use the ASR pipeline to transcribe the audio
+    with open(audio_file.name, "rb") as f:  # Change this line
+        data = f.read()
+    output = query(ASR_API_URL, data=data)
+    transcription = output["text"]
 
     # Use the translation pipeline to translate the transcription
     translated_text = query(TRANSLATION_API_URL, {"inputs": transcription})