Spaces:
Sleeping
Sleeping
File size: 3,142 Bytes
ed1c090 b5233b9 ed1c090 b5233b9 ec02589 b5233b9 ed1c090 ec02589 ed1c090 b5233b9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 |
import gradio as gr
import voice_recognition as vr
# Example lists for source and target languages
source_languages = ["English", "French", "Arabic", "MA-Arabic", "Tagalog", "Cebuano"]
target_languages = ["English", "French", "Arabic", "MA-Arabic", "Tagalog", "Cebuano"]
# Model and task options
models = ["Whisper", "Google"]
tasks = ["Transcript", "Transcript and Translate"]
# Dictionary mapping language labels to ISO codes
language_mapping = {
"English": "en",
"French": "fr",
"Arabic": "ar",
"MA-Arabic": "ar",
"Tagalog": "tl",
"Cebuano": "fil-PH"
}
# Method to get the ISO code from a language label
def get_iso_code(language_label):
return language_mapping.get(language_label, "en")
# Function to handle the input and return the selections
def process_inputs(source_lang, target_lang, model, task, audio_mic, audio_upload):
print("button submit clicked !!")
audio = None
if audio_mic:
audio = audio_mic
elif audio_upload:
audio = audio_upload
print("audio")
print(audio)
print("----")
response = vr.process_audio_recognition(model=model, audio_path=audio, source_lang=get_iso_code(source_lang),
target_lang=get_iso_code(target_lang), translate= task == "Transcript and Translate")
return response
# return {
# "Source Language": source_lang,
# "Target Language": target_lang,
# "Model": model,
# "Task": task,
# "Audio Received": "Yes" if audio else "No"
# }
# Gradio interface setup
with gr.Blocks(title = "Voice Transcription") as demo:
with gr.Row():
# Dropdown for source and target languages (display name, return ISO code)
source_lang_dropdown = gr.Dropdown(label="Source Language", choices=source_languages, value="English")
target_lang_dropdown = gr.Dropdown(label="Target Language", choices=target_languages, value="French")
with gr.Row():
# Dropdown for models and tasks
model_dropdown = gr.Dropdown(label="Model", choices=models, value=models[0], info="The model that will be used")
task_dropdown = gr.Dropdown(label="Task", choices=tasks, value=tasks[0], info="Transcript and/or Translate")
# Audio input (mic or upload)
with gr.Tab("Record"):
audio_input_mic = gr.Audio(sources=["microphone"], type="filepath")
with gr.Tab("Upload"):
audio_input_upload = gr.Audio(sources=["upload"], type="filepath")
#audio_input = gr.Audio(sources=["microphone"], type="filepath")
#audio_input2 = gr.Audio(sources=["upload"], type="filepath")
# Button to submit
submit_button = gr.Button("Submit")
# Output label to show the selected inputs
output = gr.Textbox(label="Result")
# Link button click to function
submit_button.click(fn=process_inputs,
inputs=[source_lang_dropdown, target_lang_dropdown, model_dropdown, task_dropdown, audio_input_mic, audio_input_upload],
outputs=output)
if __name__ == '__main__':
# check the model rate
demo.launch(favicon_path = "./favicon.ico")
|