File size: 1,492 Bytes
6bd1511 |
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 |
import gradio as gr
import requests
import os
import dwani
# List of supported languages
LANGUAGES = ["malayalam", "tamil", "telugu", "hindi", "kannada"]
dwani.api_key = os.getenv("DWANI_API_KEY")
dwani.api_base = os.getenv("DWANI_API_BASE_URL")
# Function to extract language name
def get_lang_name(lang_string):
return lang_string.split("(")[0].strip().lower()
def transcribe_api(audio_file, language):
# Get the base URL from environment variable
result = dwani.ASR.transcribe(file_path=audio_file, language=language)
return result
# Create Gradio interface
with gr.Blocks(title="Speech to Text API Interface") as demo:
gr.Markdown("# Speech to Text API Interface")
with gr.Row():
with gr.Column():
# Input components
audio_input = gr.Audio(
label="Audio File",
type="filepath",
sources=["upload"]
)
language_input = gr.Dropdown(
label="Language",
choices=LANGUAGES,
value="kannada"
)
submit_btn = gr.Button("Transcribe")
with gr.Column():
# Output component
output = gr.JSON(label="Transcription Response")
# Connect the button click to the API function
submit_btn.click(
fn=transcribe_api,
inputs=[audio_input, language_input],
outputs=output
)
# Launch the interface
demo.launch() |