Sistema completo de detección de highlights con VLM y análisis de gameplay
- Implementación de detector híbrido (Whisper + Chat + Audio + VLM) - Sistema de detección de gameplay real vs hablando - Scene detection con FFmpeg - Soporte para RTX 3050 y RX 6800 XT - Guía completa en 6800xt.md para próxima IA - Scripts de filtrado visual y análisis de contexto - Pipeline automatizado de generación de videos
This commit is contained in:
renato97
232
gameplay_detector.py
Normal file
232
gameplay_detector.py
Normal file
@@ -0,0 +1,232 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
GAMEPLAY ACTIVE DETECTOR
|
||||
Detecta solo momentos donde realmente está jugando (no intro, no selección, no hablando solo)
|
||||
"""
|
||||
|
||||
import json
|
||||
import re
|
||||
import numpy as np
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
def analyze_gameplay_activity(transcription_file, chat_file):
|
||||
"""
|
||||
Analiza cuándo hay gameplay activo vs cuando solo está hablando.
|
||||
|
||||
Señales de gameplay activo:
|
||||
- Chat con keywords de LoL (kill, gank, baron, etc)
|
||||
- Audio con picos (gritos, reacciones intensas)
|
||||
- Transcripción con acciones de juego (ulti, flash, etc)
|
||||
|
||||
Señales de NO gameplay:
|
||||
- Solo hablando de temas random
|
||||
- Selección de campeones
|
||||
- Esperando en base
|
||||
"""
|
||||
|
||||
print("=" * 60)
|
||||
print("GAMEPLAY ACTIVITY ANALYZER")
|
||||
print("=" * 60)
|
||||
|
||||
# Cargar datos
|
||||
with open(transcription_file, "r") as f:
|
||||
trans = json.load(f)
|
||||
|
||||
with open(chat_file, "r") as f:
|
||||
chat_data = json.load(f)
|
||||
|
||||
# Keywords que indican gameplay activo
|
||||
gameplay_keywords = [
|
||||
"kill",
|
||||
"matan",
|
||||
"muere",
|
||||
"gank",
|
||||
"gankean",
|
||||
"teamfight",
|
||||
"fight",
|
||||
"ulti",
|
||||
"ultimate",
|
||||
"flash",
|
||||
"ignite",
|
||||
"exhaust",
|
||||
"heal",
|
||||
"baron",
|
||||
"dragón",
|
||||
"dragon",
|
||||
"torre",
|
||||
"tower",
|
||||
"inhib",
|
||||
"pentakill",
|
||||
"quadra",
|
||||
"triple",
|
||||
"doble",
|
||||
"ace",
|
||||
"jungle",
|
||||
"jungla",
|
||||
"adc",
|
||||
"support",
|
||||
"top",
|
||||
"mid",
|
||||
" Warwick",
|
||||
"Diana",
|
||||
"Yasuo",
|
||||
"Zed",
|
||||
"Lee Sin",
|
||||
"campeón",
|
||||
]
|
||||
|
||||
# Analizar cada segundo del video
|
||||
duration = int(max(seg["end"] for seg in trans["segments"])) + 1
|
||||
gameplay_score = np.zeros(duration)
|
||||
|
||||
# 1. Puntuar por transcripción
|
||||
for seg in trans["segments"]:
|
||||
text = seg["text"].lower()
|
||||
start = int(seg["start"])
|
||||
end = int(seg["end"])
|
||||
|
||||
score = 0
|
||||
# Keywords de gameplay
|
||||
for kw in gameplay_keywords:
|
||||
if kw in text:
|
||||
score += 2
|
||||
|
||||
# Acciones específicas
|
||||
if any(word in text for word in ["me mataron", "me mori", "kill", "mate"]):
|
||||
score += 5
|
||||
if any(word in text for word in ["ulti", "flash", "ignite"]):
|
||||
score += 3
|
||||
if any(word in text for word in ["joder", "puta", "mierda", "no puede ser"]):
|
||||
score += 2
|
||||
|
||||
# Penalizar selección de campeones y temas off-topic
|
||||
if any(
|
||||
word in text for word in ["champions", "selección", "ban", "pick", "elijo"]
|
||||
):
|
||||
score -= 10 # Penalizar fuerte selección
|
||||
if any(
|
||||
word in text for word in ["cuento", "historia", "ayer", "mañana", "comida"]
|
||||
):
|
||||
score -= 5 # Penalizar charla random
|
||||
|
||||
for i in range(start, min(end + 1, duration)):
|
||||
gameplay_score[i] += score
|
||||
|
||||
# 2. Puntuar por chat
|
||||
chat_activity = np.zeros(duration)
|
||||
for comment in chat_data["comments"]:
|
||||
sec = int(comment["content_offset_seconds"])
|
||||
if sec < duration:
|
||||
msg = comment["message"]["body"].lower()
|
||||
|
||||
# Chat sobre gameplay
|
||||
for kw in gameplay_keywords:
|
||||
if kw in msg:
|
||||
chat_activity[sec] += 1
|
||||
|
||||
# Mucha actividad = probablemente gameplay intenso
|
||||
chat_activity[sec] += 0.5
|
||||
|
||||
# Suavizar chat
|
||||
from scipy.ndimage import uniform_filter1d
|
||||
|
||||
chat_smooth = uniform_filter1d(chat_activity, size=5, mode="constant")
|
||||
|
||||
# Combinar scores
|
||||
gameplay_score += chat_smooth * 2
|
||||
|
||||
# Suavizar resultado
|
||||
gameplay_smooth = uniform_filter1d(gameplay_score, size=15, mode="constant")
|
||||
|
||||
# Encontrar regiones de gameplay activo
|
||||
threshold = np.percentile(gameplay_smooth[gameplay_smooth > 0], 40)
|
||||
print(f"Umbral de gameplay: {threshold:.1f}")
|
||||
|
||||
active_regions = []
|
||||
in_gameplay = False
|
||||
region_start = 0
|
||||
|
||||
for i in range(455, len(gameplay_smooth)): # Saltar intro
|
||||
if gameplay_smooth[i] > threshold:
|
||||
if not in_gameplay:
|
||||
region_start = i
|
||||
in_gameplay = True
|
||||
else:
|
||||
if in_gameplay:
|
||||
if i - region_start >= 20: # Mínimo 20 segundos
|
||||
active_regions.append((region_start, i))
|
||||
in_gameplay = False
|
||||
|
||||
# Capturar última región
|
||||
if in_gameplay and len(gameplay_smooth) - region_start >= 20:
|
||||
active_regions.append((region_start, len(gameplay_smooth)))
|
||||
|
||||
print(f"Regiones de gameplay activo: {len(active_regions)}")
|
||||
|
||||
return active_regions, gameplay_smooth
|
||||
|
||||
|
||||
def filter_rage_moments(rage_moments, gameplay_regions, min_overlap=0.5):
|
||||
"""
|
||||
Filtra momentos de rage para mantener solo los que ocurren durante gameplay activo.
|
||||
|
||||
Args:
|
||||
rage_moments: Lista de momentos de rage
|
||||
gameplay_regions: Lista de (start, end) con gameplay activo
|
||||
min_overlap: Mínimo porcentaje de superposición requerida
|
||||
"""
|
||||
filtered = []
|
||||
|
||||
for moment in rage_moments:
|
||||
moment_start = moment["start"]
|
||||
moment_end = moment["end"]
|
||||
moment_duration = moment_end - moment_start
|
||||
|
||||
# Buscar si hay gameplay activo durante este momento
|
||||
best_overlap = 0
|
||||
best_region = None
|
||||
|
||||
for g_start, g_end in gameplay_regions:
|
||||
# Calcular superposición
|
||||
overlap_start = max(moment_start, g_start)
|
||||
overlap_end = min(moment_end, g_end)
|
||||
overlap_duration = max(0, overlap_end - overlap_start)
|
||||
|
||||
if overlap_duration > best_overlap:
|
||||
best_overlap = overlap_duration
|
||||
best_region = (g_start, g_end)
|
||||
|
||||
# Si hay suficiente superposición, mantener el momento
|
||||
if best_region and best_overlap >= moment_duration * min_overlap:
|
||||
# Ajustar límites al gameplay activo
|
||||
new_start = max(moment_start, best_region[0] - 5) # 5s antes
|
||||
new_end = min(moment_end, best_region[1] + 10) # 10s después
|
||||
|
||||
moment["start"] = int(new_start)
|
||||
moment["end"] = int(new_end)
|
||||
moment["gameplay_overlap"] = best_overlap
|
||||
filtered.append(moment)
|
||||
|
||||
print(f"Momentos filtrados (solo gameplay): {len(filtered)} de {len(rage_moments)}")
|
||||
return filtered
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 1. Detectar gameplay activo
|
||||
regions, scores = analyze_gameplay_activity(
|
||||
"transcripcion_rage.json", "elxokas_chat.json"
|
||||
)
|
||||
|
||||
print("\nRegiones de gameplay:")
|
||||
for i, (s, e) in enumerate(regions[:10], 1):
|
||||
mins_s, secs_s = divmod(s, 60)
|
||||
mins_e, secs_e = divmod(e, 60)
|
||||
dur = e - s
|
||||
print(f"{i}. {mins_s:02d}:{secs_s:02d} - {mins_e:02d}:{secs_e:02d} ({dur}s)")
|
||||
|
||||
# Guardar regiones
|
||||
with open("gameplay_regions.json", "w") as f:
|
||||
json.dump(regions, f)
|
||||
|
||||
print(f"\nGuardado en gameplay_regions.json")
|
||||
Reference in New Issue
Block a user