ParulPandey commited on
Commit
9815cd6
·
verified ·
1 Parent(s): ed90568

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +5 -9
app.py CHANGED
@@ -571,7 +571,7 @@ def main_ui():
571
  with gr.Column(elem_classes=["asha-section"]):
572
  gr.Markdown(
573
  """
574
- # ASHA Form Digitizer & Hindi Voice Transcriber
575
  ### **Digitizing rural health, empowering ASHA workers with AI.**
576
 
577
  This application is designed to help **ASHA (Accredited Social Health Activist) workers**—the backbone of India's rural healthcare system—quickly digitize handwritten forms and transcribe Hindi voice input. ASHA workers are often the first point of contact for healthcare in villages, but their work is slowed by manual paperwork and language barriers. This tool streamlines their workflow, making data entry faster, more accurate, and accessible even for those more comfortable with Hindi speech than typing.
@@ -580,20 +580,16 @@ This application is designed to help **ASHA (Accredited Social Health Activist)
580
  - **Hindi voice transcription:** Fill any field by speaking in Hindi (Devanagari script) for instant, accurate transcription.
581
  - **Data export:** All submitted data is saved in a CSV for further use or analysis.
582
 
583
- ---
584
-
585
- **Powered by Gemma 3n 4B**
586
  This demo runs on the **Gemma 3n 4B model**, a lightweight yet capable model for on-device AI tasks like image-to-text and Hindi speech transcription.
587
 
588
- **On-device CPU Loading**
589
  Since this application runs entirely **on-device using CPU**, the model takes some time to **load the first time**. After the initial load, processing is smooth and does not require an internet connection.
590
 
591
- ---
592
-
593
- **Why this matters:**
594
  ASHA workers serve over 900 million people in rural India, often with limited digital literacy and resources. By making form digitization and voice transcription seamless, this app saves time, reduces errors, and helps bring rural health data into the digital age—empowering both workers and the communities they serve.
595
 
596
- **Note:**
597
  While you are reading this, the **Gemma 3n model** is being loaded in the background to ensure a smooth and fast demo experience. Please explore each step—the workflow is strictly gated for demo clarity. All features are designed for real-world usability and hackathon evaluation.
598
  """,
599
  elem_id="asha_about"
 
571
  with gr.Column(elem_classes=["asha-section"]):
572
  gr.Markdown(
573
  """
574
+ # ON DEVICE SMART ASHA Form
575
  ### **Digitizing rural health, empowering ASHA workers with AI.**
576
 
577
  This application is designed to help **ASHA (Accredited Social Health Activist) workers**—the backbone of India's rural healthcare system—quickly digitize handwritten forms and transcribe Hindi voice input. ASHA workers are often the first point of contact for healthcare in villages, but their work is slowed by manual paperwork and language barriers. This tool streamlines their workflow, making data entry faster, more accurate, and accessible even for those more comfortable with Hindi speech than typing.
 
580
  - **Hindi voice transcription:** Fill any field by speaking in Hindi (Devanagari script) for instant, accurate transcription.
581
  - **Data export:** All submitted data is saved in a CSV for further use or analysis.
582
 
583
+ ## Powered by Gemma-3n-4B
 
 
584
  This demo runs on the **Gemma 3n 4B model**, a lightweight yet capable model for on-device AI tasks like image-to-text and Hindi speech transcription.
585
 
586
+ ## On-device CPU Loading
587
  Since this application runs entirely **on-device using CPU**, the model takes some time to **load the first time**. After the initial load, processing is smooth and does not require an internet connection.
588
 
589
+ ## Why this matters
 
 
590
  ASHA workers serve over 900 million people in rural India, often with limited digital literacy and resources. By making form digitization and voice transcription seamless, this app saves time, reduces errors, and helps bring rural health data into the digital age—empowering both workers and the communities they serve.
591
 
592
+ *Note:*
593
  While you are reading this, the **Gemma 3n model** is being loaded in the background to ensure a smooth and fast demo experience. Please explore each step—the workflow is strictly gated for demo clarity. All features are designed for real-world usability and hackathon evaluation.
594
  """,
595
  elem_id="asha_about"