Fix file transcribation

app.py

@@ -2,10 +2,12 @@ import gradio as gr
 from transformers import pipeline
 import numpy as np
 
-transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
+transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en", return_timestamps=True)
 
 
 def transcribe(stream, new_chunk):
+    # if stream is not None:
+        # print(stream.shape, new_chunk)
     sr, y = new_chunk
 
     # Convert to mono if stereo
@@ -19,14 +21,16 @@ def transcribe(stream, new_chunk):
         stream = np.concatenate([stream, y])
     else:
         stream = y
-    return stream, transcriber({"sampling_rate": sr, "raw": stream})["text"]
+    text = transcriber({"sampling_rate": sr, "raw": stream})["text"]
+    # print(text)
+    return stream, text
 
 
 demo = gr.Interface(
     transcribe,
     ["state", gr.Audio(sources=["upload"], streaming=False)],
     ["state", "text"],
-    live=True,
+    # live=True,
 )
 
 demo.launch()

requirements.txt

@@ -1,3 +1,4 @@
 transformers
 numpy
 torch
+torchaudio