Fix audio loading script

app.py

@@ -1,9 +1,15 @@
 import gradio as gr
 from transformers import pipeline
-from librosa import load
+from librosa import resample
 
 def transcribe(input_audio):
-    speech, _ = load(input_audio, sr=16000, mono=True)
+    sr, speech = input_audio
+    # Convert to mono if stereo
+    if speech.ndim > 1:
+        speech = speech.mean(axis=1)
+    # Resample if sampling rate is not 16kHz
+    if sr!=16000:
+        speech = librosa.resample(speech, orig_sr=sr, target_sr=16000)
     output = pipe(speech, chunk_length_s=30, stride_length_s=5)['text']
     return output
 

requirements.txt

@@ -1,3 +1,5 @@
 transformers
 torch
-librosa
+librosa
+samplerate
+resampy