Spaces:
Sleeping
Sleeping
base code
Browse files- requirements.txt +6 -0
- views/real_time.py +80 -0
requirements.txt
CHANGED
@@ -8,3 +8,9 @@ numpy
|
|
8 |
pandas
|
9 |
matplotlib
|
10 |
scikit-learn
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
pandas
|
9 |
matplotlib
|
10 |
scikit-learn
|
11 |
+
streamlit
|
12 |
+
streamlit_option_menu
|
13 |
+
torchaudio
|
14 |
+
huggingface
|
15 |
+
huggingface_hub
|
16 |
+
pyaudio
|
views/real_time.py
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
################################
|
2 |
+
### NOT YET TESTED
|
3 |
+
###############################
|
4 |
+
|
5 |
+
import streamlit as st
|
6 |
+
import pyaudio
|
7 |
+
import wave
|
8 |
+
import torch
|
9 |
+
from transformers import Wav2Vec2ForSequenceClassification, Wav2Vec2Processor
|
10 |
+
import numpy as np
|
11 |
+
import time
|
12 |
+
|
13 |
+
# Charger le modèle Wav2Vec2 pour la classification des émotions
|
14 |
+
model_name = "superb/wav2vec2-base-superb-er" # Exemple de modèle pour la reconnaissance des émotions
|
15 |
+
processor = Wav2Vec2Processor.from_pretrained(model_name)
|
16 |
+
model = Wav2Vec2ForSequenceClassification.from_pretrained(model_name)
|
17 |
+
|
18 |
+
# Paramètres audio
|
19 |
+
CHUNK = 1024
|
20 |
+
FORMAT = pyaudio.paInt16
|
21 |
+
CHANNELS = 1
|
22 |
+
RATE = 16000
|
23 |
+
|
24 |
+
# Fonction pour prédire l'émotion à partir d'un segment audio
|
25 |
+
def predict_emotion(audio_data):
|
26 |
+
inputs = processor(audio_data, sampling_rate=RATE, return_tensors="pt", padding=True)
|
27 |
+
with torch.no_grad():
|
28 |
+
logits = model(**inputs).logits
|
29 |
+
predicted_id = torch.argmax(logits, dim=-1).item()
|
30 |
+
emotion = model.config.id2label[predicted_id]
|
31 |
+
return emotion
|
32 |
+
|
33 |
+
# Interface Streamlit
|
34 |
+
st.title("Détection des émotions en temps réel")
|
35 |
+
|
36 |
+
# Boutons pour démarrer et arrêter l'enregistrement
|
37 |
+
start_button = st.button("Démarrer l'enregistrement")
|
38 |
+
stop_button = st.button("Arrêter l'enregistrement")
|
39 |
+
|
40 |
+
# Zone de visualisation des émotions en temps réel
|
41 |
+
emotion_placeholder = st.empty()
|
42 |
+
final_emotion_placeholder = st.empty()
|
43 |
+
|
44 |
+
if start_button:
|
45 |
+
st.write("Enregistrement en cours...")
|
46 |
+
audio = pyaudio.PyAudio()
|
47 |
+
stream = audio.open(format=FORMAT, channels=CHANNELS, rate=RATE, input=True, frames_per_buffer=CHUNK)
|
48 |
+
|
49 |
+
frames = []
|
50 |
+
real_time_emotions = []
|
51 |
+
|
52 |
+
while not stop_button:
|
53 |
+
data = stream.read(CHUNK)
|
54 |
+
frames.append(data)
|
55 |
+
|
56 |
+
# Traitement en temps réel (par tranche de 1 seconde)
|
57 |
+
if len(frames) >= RATE // CHUNK:
|
58 |
+
audio_segment = np.frombuffer(b''.join(frames[-(RATE // CHUNK):]), dtype=np.int16)
|
59 |
+
emotion = predict_emotion(audio_segment)
|
60 |
+
real_time_emotions.append(emotion)
|
61 |
+
emotion_placeholder.line_chart(real_time_emotions) # Affichage graphique des émotions
|
62 |
+
|
63 |
+
# Arrêt de l'enregistrement
|
64 |
+
stream.stop_stream()
|
65 |
+
stream.close()
|
66 |
+
audio.terminate()
|
67 |
+
|
68 |
+
# Sauvegarde de l'audio enregistré
|
69 |
+
wf = wave.open("output.wav", "wb")
|
70 |
+
wf.setnchannels(CHANNELS)
|
71 |
+
wf.setsampwidth(audio.get_sample_size(FORMAT))
|
72 |
+
wf.setframerate(RATE)
|
73 |
+
wf.writeframes(b"".join(frames))
|
74 |
+
wf.close()
|
75 |
+
|
76 |
+
# Prédiction finale sur tout l'audio enregistré
|
77 |
+
full_audio_data = np.frombuffer(b''.join(frames), dtype=np.int16)
|
78 |
+
final_emotion = predict_emotion(full_audio_data)
|
79 |
+
|
80 |
+
final_emotion_placeholder.write(f"Émotion finale prédite : {final_emotion}")
|