Spaces:
Runtime error
Runtime error
implemented the audio function
Browse files
app.py
CHANGED
@@ -228,13 +228,15 @@ def process_and_query(text, image,audio):
|
|
228 |
text = process_image_with_openai(image)
|
229 |
|
230 |
if audio is not None:
|
231 |
-
audio = audio[0].numpy()
|
232 |
-
audio = audio.astype(np.float32)
|
233 |
-
audio = audio / np.max(np.abs(audio))
|
234 |
-
audio = audio * 32768
|
235 |
-
audio = audio.astype(np.int16)
|
236 |
-
audio = audio.tobytes()
|
237 |
-
audio = base64.b64encode(audio).decode('utf-8')
|
|
|
|
|
238 |
|
239 |
# Now, use the text (either provided by the user or obtained from OpenAI) to query Vectara
|
240 |
vectara_response_json = query_vectara(text)
|
|
|
228 |
text = process_image_with_openai(image)
|
229 |
|
230 |
if audio is not None:
|
231 |
+
# audio = audio[0].numpy()
|
232 |
+
# audio = audio.astype(np.float32)
|
233 |
+
# audio = audio / np.max(np.abs(audio))
|
234 |
+
# audio = audio * 32768
|
235 |
+
# audio = audio.astype(np.int16)
|
236 |
+
# audio = audio.tobytes()
|
237 |
+
# audio = base64.b64encode(audio).decode('utf-8')
|
238 |
+
text = process_speech(audio)
|
239 |
+
return text
|
240 |
|
241 |
# Now, use the text (either provided by the user or obtained from OpenAI) to query Vectara
|
242 |
vectara_response_json = query_vectara(text)
|