Create app.py

app.py

@@ -0,0 +1,75 @@
+# Import necessary libraries and filter warnings
+import warnings
+warnings.filterwarnings("ignore")
+
+import os
+import re
+import torchaudio
+import gradio as gr
+import numpy as np
+from transformers import pipeline
+from transformers import AutoProcessor
+from pyctcdecode import build_ctcdecoder
+from transformers import Wav2Vec2ProcessorWithLM
+from text2int import text_to_int
+from isNumber import is_number
+from Text2List import text_to_list
+from convert2list import convert_to_list
+from processDoubles import process_multiples
+from replaceWords import replace_words
+
+pipe = pipeline(task="automatic-speech-recognition", model="C:/Users/WCHL/Desktop/huggingface_english/hf_eng")
+
+
+def transcribe_english(audio):
+    # # Process the audio file
+    transcript = pipe(audio)
+    text_value = transcript['text']
+    cleaned_text=text_value.replace("<s>", "")
+    converted_to_list=convert_to_list(cleaned_text,text_to_list())
+    processd_multiples=process_multiples(converted_to_list)
+    replaced_words = replace_words(processd_multiples)
+    converted_text=text_to_int(replaced_words)
+    return converted_text
+    
+# def sel_lng(lng, mic=None, file=None):
+#     if mic is not None:
+#         audio = mic
+#     elif file is not None:
+#         audio = file
+#     else:
+#         return "You must either provide a mic recording or a file"
+    
+#     if lng == "model_1":
+#         return transcribe_hindi_old(audio)
+#     elif lng == "model_2":
+#         return transcribe_hindi_new(audio)
+#     elif lng== "model_3":
+#         return transcribe_hindi_lm(audio)
+        
+demo=gr.Interface(
+    transcribe_english,
+    inputs=[
+        gr.Audio(sources=["microphone","upload"], type="filepath"),
+    ],
+    outputs=[
+        "textbox"
+    ],
+    title="Automatic Speech Recognition",
+    description = "Demo for Automatic Speech Recognition. Use microphone to record speech. Please press Record button. Initially it will take some time to load the model. The recognized text will appear in the output textbox",
+      ).launch()
+
+# demo=gr.Interface(
+#     fn=sel_lng, 
+      
+#     inputs=[
+#         gr.Dropdown([
+#             "model_1","model_2","model_3"],label="Select Model"),
+#         gr.Audio(sources=["microphone","upload"], type="filepath"),
+#     ],
+#     outputs=[
+#         "textbox"
+#     ],
+#     title="Automatic Speech Recognition",
+#     description = "Demo for Automatic Speech Recognition. Use microphone to record speech. Please press Record button. Initially it will take some time to load the model. The recognized text will appear in the output textbox",
+#       ).launch()