File size: 5,648 Bytes
9683cd0 51558b1 9683cd0 51558b1 9683cd0 51558b1 9683cd0 |
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 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 |
import gradio as gr
import os
import requests
from transformers import pipeline
# Set your FastAPI backend endpoint
BACKEND_URL = "https://35d2-41-84-202-90.ngrok-free.app/submit-feedback"
# Map of models
model_map = {
"english": "jonatasgrosman/wav2vec2-large-xlsr-53-english"
}
# Create storage directory
os.makedirs("responses", exist_ok=True)
# Transcription function
def transcribe(audio, language):
asr = pipeline("automatic-speech-recognition", model=model_map[language], device=0)
text = asr(audio)["text"]
return text, audio
# Save feedback by sending it to FastAPI backend
def save_feedback(audio_file, transcription, age_group, gender, evaluated_language, speak_level, write_level,
native, native_language, env, device, domain, accuracy, orthography, meaning, errors,
performance, improvement, usability, technical_issues, final_comments, email):
try:
# Read binary content of audio file
with open(audio_file, "rb") as f:
audio_content = f.read()
# Prepare metadata as form fields
metadata = {
"transcription": transcription,
"age_group": age_group,
"gender": gender,
"evaluated_language": evaluated_language,
"speak_level": speak_level,
"write_level": write_level,
"native": native,
"native_language": native_language,
"environment": env,
"device": device,
"domain": domain,
"accuracy": accuracy,
"orthography": orthography,
"meaning": meaning,
"errors": ",".join(errors) if errors else "",
"performance": performance,
"improvement": improvement,
"usability": usability,
"technical_issues": technical_issues,
"final_comments": final_comments,
"email": email
}
files = {
"audio_file": ("audio.wav", audio_content, "audio/wav")
}
response = requests.post(BACKEND_URL, data=metadata, files=files, timeout=20)
if response.status_code == 201:
return "✅ Feedback submitted successfully. Thank you!"
else:
return f"⚠️ Submission failed: {response.status_code} — {response.text}"
except Exception as e:
return f"❌ Could not connect to the backend: {str(e)}"
# Gradio UI
with gr.Blocks() as demo:
gr.Markdown("## African ASR + Feedback")
with gr.Row():
audio_input = gr.Audio(sources=["upload", "microphone"], type="filepath", label="Upload or record audio")
lang = gr.Dropdown(list(model_map.keys()), label="Select Language")
transcribed_text = gr.Textbox(label="Transcribed Text")
submit_btn = gr.Button("Transcribe")
submit_btn.click(fn=transcribe, inputs=[audio_input, lang], outputs=[transcribed_text, audio_input])
gr.Markdown("---\n## Feedback Form")
age_group = gr.Dropdown(["18 to 30", "31 to 50", "50+", "Prefer not to say"], label="Age Group")
gender = gr.Dropdown(["Male", "Female", "Prefer not to say", "Other"], label="Gender")
evaluated_language = gr.Dropdown(list(model_map.keys()), label="Which language did you evaluate for?")
speak_level = gr.Slider(1, 10, label="How well do you speak this language?")
write_level = gr.Slider(1, 10, label="How well do you write the language?")
native = gr.Radio(["Yes", "No"], label="Are you a native speaker of this language?")
native_language = gr.Textbox(label="If not, what is your native language?")
env = gr.Dropdown(["Studio/Professional Recording", "Quiet Room", "Noisy Background", "Multiple Environments", "Unsure", "Other"], label="Recording environment")
device = gr.Dropdown(["Mobile Phone/Tablet", "Tablet", "Laptop/Computer Microphone", "Dedicated Microphone", "Unsure", "Other"], label="Recording device")
domain = gr.Textbox(label="Was the speech related to a specific domain or topic? (Optional)")
accuracy = gr.Slider(1, 10, label="How accurate was the model’s transcription?")
orthography = gr.Dropdown(["Yes, mostly correct", "No, major issues", "Partially", "Not Applicable"], label="Did the transcription use standard orthography?")
meaning = gr.Slider(1, 10, label="Did the transcription preserve the original meaning?")
errors = gr.CheckboxGroup([
"Substitutions", "Omissions", "Insertions", "Pronunciation-related", "Diacritic Errors",
"Code-switching Errors", "Named Entity Errors", "Punctuation Errors", "No significant errors"
], label="Which errors were prominent?")
performance = gr.Textbox(label="What did the model do well? What did it struggle with?")
improvement = gr.Textbox(label="How could this ASR model be improved?")
usability = gr.Slider(1, 5, label="How easy was it to use the tool?")
technical_issues = gr.Textbox(label="Did you encounter any technical issues?")
final_comments = gr.Textbox(label="Any other comments or suggestions?")
email = gr.Textbox(label="Email (optional)")
save_btn = gr.Button("Submit Feedback")
output_msg = gr.Textbox(interactive=False)
save_btn.click(fn=save_feedback,
inputs=[audio_input, transcribed_text, age_group, gender, evaluated_language, speak_level, write_level,
native, native_language, env, device, domain, accuracy, orthography, meaning, errors,
performance, improvement, usability, technical_issues, final_comments, email],
outputs=[output_msg])
# Launch the interface
demo.launch()
|