Update app.py

app.py

@@ -2,14 +2,13 @@ from transformers import pipeline
 import os
 import gradio as gr
 import torch
-from IPython.display import Audio as IPythonAudio
-from gtts import gTTS
-import IPython.display as ipd
+#from IPython.display import Audio as IPythonAudio
+#from gtts import gTTS
+#import IPython.display as ipd
 
 #Audio to text
-asr = pipeline(task="automatic-speech-recognition",
-             model="distil-whisper/distil-small.en")
-#asr=pipeline("automatic-speech-recognition",              model="openai/whisper-large-v3")
+#asr = pipeline(task="automatic-speech-recognition",
+#             model="distil-whisper/distil-small.en")
 #Text to text
 translator = pipeline(task="translation",
                       model="facebook/nllb-200-distilled-600M",
@@ -23,7 +22,8 @@ def transcribe_speech(filepath):
     if filepath is None:
         gr.Warning("No audio found, please retry.")
         return ""
-    output = translator(asr(filepath)["text"],
+    #asr(filepath)["text"]    
+    output = translator(filepath,
                              src_lang="eng_Latn",
                              tgt_lang="hin_Deva")
     narrated_text=pipe(output[0]['translation_text'])
@@ -35,16 +35,18 @@ def transcribe_speech(filepath):
     
 mic_transcribe = gr.Interface(
     fn=transcribe_speech,
-    inputs=gr.Audio(sources="microphone",
-                    type="filepath"),
+    #inputs=gr.Audio(sources="microphone",
+    #                type="filepath"),
+    inputs=gr.Textbox(label="text",lines=3),
     outputs="audio",
     #outputs=gr.Audio(label="Translated Message"),
     allow_flagging="never")
 
 file_transcribe = gr.Interface(
     fn=transcribe_speech,
-    inputs=gr.Audio(sources="upload",
-                    type="filepath"),
+    #inputs=gr.Audio(sources="upload",
+    #                type="filepath"),
+    inputs=gr.Textbox(label="text",lines=3),
     outputs="audio",
     #outputs=gr.Audio(label="Translated Message"),
     allow_flagging="never"