Update app.py

app.py

@@ -1,42 +1,18 @@
-
-# import gradio as gr
-# from googletrans import Translator
-# import torch
-# # Initialize Translator
-# from transformers import pipeline
-# translator = Translator()
-# MODEL_NAME = "openai/whisper-base"
-# device = 0 if torch.cuda.is_available() else "cpu"
-# pipe = pipeline(
-# task="automatic-speech-recognition",
-# model=MODEL_NAME,
-# chunk_length_s=30,
-# device=device,
-# )
-
-
-# def transcribe_audio(audio):
-# text = pipe(audio)["text"]
-# return text
-# # return translated_text
-
-# audio_record = gr.inputs.Audio(source='microphone', label='Record Audio')
-# output_text = gr.outputs.Textbox(label='Transcription')
-
-# interface = gr.Interface(fn=transcribe_audio, inputs=audio_record, outputs=output_text)
-# interface.launch()
-
 import gradio as gr
 from transformers import pipeline
 
-modelo = pipeline("automatic-speech-recognition", model="openai/whisper-base")
+# Load the automatic speech recognition pipeline
+asr_pipeline = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-large-960h")
+
+def transcribe_audio(audio):
+ # Transcribe the audio input
+ transcription = asr_pipeline(audio)[0]["transcription"]
+ return transcription
 
-def transcribe(audio):
- text = modelo(audio)["text"]
- return text
+# Define Gradio interface
+audio_input = gr.inputs.Audio(source="microphone", type="auto", label="Record Audio")
+text_output = gr.outputs.Textbox(label="Transcription")
 
-gr.Interface(
- fn=transcribe,
- inputs=[gr.Audio(source="microphone", type="filepath")],
- outputs=["textbox"]
-).launch()
+# Create the interface and launch it
+interface = gr.Interface(fn=transcribe_audio, inputs=audio_input, outputs=text_output, title="Speech to Text")
+interface.launch()