Spaces:
Sleeping
Sleeping
File size: 2,599 Bytes
cc9c39b 67a8fe6 cc9c39b 67a8fe6 de622d7 67a8fe6 de622d7 67a8fe6 cc9c39b 67a8fe6 |
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 |
import gradio as gr
from transformers import pipeline
from PIL import Image
TEXT_MODEL = "j-hartmann/emotion-english-distilroberta-base"
IMAGE_MODEL = "trpakov/vit-face-expression"
AUDIO_MODEL = "superb/hubert-large-superb-er"
text_pipe = pipeline("text-classification", model=TEXT_MODEL, return_all_scores=True)
image_pipe = pipeline("image-classification", model=IMAGE_MODEL, top_k=None)
audio_pipe = pipeline("audio-classification", model=AUDIO_MODEL, top_k=None)
def _as_label_dict(preds):
preds_sorted = sorted(preds, key=lambda p: p["score"], reverse=True)
return {p["label"]: float(round(p["score"], 4)) for p in preds_sorted}
def analyze_text(text: str):
if not text or not text.strip():
return {"(enter some text)": 1.0}
preds = text_pipe(text)[0]
return _as_label_dict(preds)
def analyze_face(img):
if img is None:
return {"(no image)": 1.0}
if isinstance(img, Image.Image):
pil = img
else:
pil = Image.fromarray(img)
preds = image_pipe(pil)
return _as_label_dict(preds)
def analyze_voice(audio_path):
if audio_path is None:
return {"(no audio)": 1.0}
preds = audio_pipe(audio_path)
return _as_label_dict(preds)
with gr.Blocks(title="Empath AI — Multimodal Emotion Detection") as demo:
gr.Markdown(
"""
# Empath AI — Emotion Detection (Text • Face • Voice)
Grant permission when the browser asks for **camera/microphone**.
Nothing is stored; analysis happens in memory and the scores are shown back to you.
"""
)
with gr.Tab("Text"):
t_in = gr.Textbox(label="Enter text", lines=3, placeholder="Type something here…")
t_btn = gr.Button("Analyze Text", variant="primary")
t_out = gr.Label(num_top_classes=3)
t_btn.click(analyze_text, inputs=t_in, outputs=t_out)
with gr.Tab("Face (Webcam or Upload)"):
i_in = gr.Image(sources=["webcam", "upload"], type="pil", label="Webcam / Upload")
i_btn = gr.Button("Analyze Face", variant="primary")
i_out = gr.Label(num_top_classes=3)
i_btn.click(analyze_face, inputs=i_in, outputs=i_out)
with gr.Tab("Voice (Mic or Upload)"):
a_in = gr.Audio(sources=["microphone", "upload"], type="filepath",
label="Record or upload a short clip (≤30s)")
a_btn = gr.Button("Analyze Voice", variant="primary")
a_out = gr.Label(num_top_classes=3)
a_btn.click(analyze_voice, inputs=a_in, outputs=a_out)
demo.launch()
|