Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,4 +1,3 @@
|
|
| 1 |
-
|
| 2 |
import os
|
| 3 |
import re
|
| 4 |
import xml.etree.ElementTree as ET
|
|
@@ -7,7 +6,7 @@ from typing import List
|
|
| 7 |
import gradio as gr
|
| 8 |
|
| 9 |
# Optional LLM (Gemini)
|
| 10 |
-
USE_LLM_DEFAULT = True
|
| 11 |
GEMINI_API_KEY = os.getenv("GEMINI_API_KEY", "").strip()
|
| 12 |
|
| 13 |
LLM_AVAILABLE = False
|
|
@@ -59,7 +58,7 @@ def frames_to_timecode(frames: int, fps: int = FPS) -> str:
|
|
| 59 |
def parse_transcript(txt: str) -> List[Segment]:
|
| 60 |
lines = [l.strip() for l in txt.splitlines() if l.strip()]
|
| 61 |
results: List[Segment] = []
|
| 62 |
-
pat_range = re.compile(r"^\[?\s*(\d{2}:\d{2}:\d{2}[:;]\d{2})\s*[
|
| 63 |
pat_point = re.compile(r"^(\d{2}:\d{2}:\d{2}[:;]\d{2})\s+(.*)$")
|
| 64 |
for l in lines:
|
| 65 |
m = pat_range.match(l)
|
|
@@ -78,14 +77,15 @@ def parse_transcript(txt: str) -> List[Segment]:
|
|
| 78 |
s, text = m.groups()
|
| 79 |
try:
|
| 80 |
s_f = parse_timecode_to_frames(s)
|
| 81 |
-
e_f = s_f + 4*FPS
|
| 82 |
e = frames_to_timecode(e_f)
|
| 83 |
results.append(Segment(s, e, s_f, e_f, text, 0.0))
|
| 84 |
except Exception:
|
| 85 |
continue
|
| 86 |
return results
|
| 87 |
|
| 88 |
-
def keyword_score(text: str
|
|
|
|
| 89 |
t = text.lower()
|
| 90 |
kw_emotion = ["medo", "coragem", "raiva", "chorei", "feliz", "triste", "emocion", "culpa", "vergonha", "orgulho"]
|
| 91 |
kw_break = ["nunca", "de repente", "contraintuitivo", "ninguém te conta", "parei", "decidi", "quebrei", "virada"]
|
|
@@ -93,48 +93,71 @@ def keyword_score(text: str) -> float:
|
|
| 93 |
kw_viral = ["segredo", "verdade", "por trás", "3 passos", "passo a passo", "como eu", "ninguém fala"]
|
| 94 |
|
| 95 |
score = 0.0
|
| 96 |
-
for kw in kw_emotion: score +=
|
| 97 |
-
for kw in kw_break: score +=
|
| 98 |
-
for kw in kw_learn: score +=
|
| 99 |
-
for kw in kw_viral: score +=
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
score += 0.2 * text.count("!")
|
| 101 |
score += 0.0005 * len(text)
|
| 102 |
return score
|
| 103 |
|
| 104 |
-
def llm_rank_segments(candidates: List[Segment]) -> List[Segment]:
|
| 105 |
-
"""Ask the LLM to pick
|
| 106 |
if not LLM_AVAILABLE:
|
| 107 |
-
return candidates
|
|
|
|
| 108 |
sample = "\n".join([f"{i}. [{c.start_tc}-{c.end_tc}] {c.text[:300]}" for i, c in enumerate(candidates)])
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
"
|
| 112 |
-
|
| 113 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
try:
|
| 115 |
-
r = LLM.generate_content(
|
| 116 |
txt = (r.text or "").strip()
|
| 117 |
idxs = [int(x) for x in re.findall(r"\d+", txt)]
|
| 118 |
idxs = [i for i in idxs if 0 <= i < len(candidates)]
|
| 119 |
-
if
|
|
|
|
|
|
|
| 120 |
return [candidates[i] for i in idxs]
|
| 121 |
-
except Exception:
|
| 122 |
-
|
| 123 |
-
|
| 124 |
-
|
| 125 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 126 |
segs = parse_transcript(transcript_txt)
|
| 127 |
if not segs:
|
| 128 |
raise ValueError("Nenhum trecho válido encontrado na transcrição.")
|
|
|
|
| 129 |
for s in segs:
|
| 130 |
-
s.score = keyword_score(s.text)
|
| 131 |
-
|
| 132 |
segs.sort(key=lambda x: x.score, reverse=True)
|
| 133 |
-
top = segs[:
|
|
|
|
| 134 |
if use_llm and LLM_AVAILABLE:
|
| 135 |
-
ranked = llm_rank_segments(top)
|
| 136 |
-
return ranked
|
| 137 |
-
|
|
|
|
| 138 |
|
| 139 |
# ---- XML editing ----
|
| 140 |
def get_sequence(root: ET.Element) -> ET.Element:
|
|
@@ -242,13 +265,18 @@ def edit_sequence_with_segments(tree: ET.ElementTree, segs: List[Segment]) -> ET
|
|
| 242 |
return tree
|
| 243 |
|
| 244 |
# ---- Gradio app ----
|
| 245 |
-
def process_xml_and_transcript(premiere_xml_file, transcript_txt_file, use_llm
|
|
|
|
|
|
|
| 246 |
if premiere_xml_file is None or transcript_txt_file is None:
|
| 247 |
return "Envie o XML do Premiere e a transcrição em .txt.", None, f"LLM disponível: {LLM_AVAILABLE}"
|
|
|
|
| 248 |
with open(transcript_txt_file.name, "r", encoding="utf-8") as f:
|
| 249 |
transcript = f.read()
|
| 250 |
|
| 251 |
-
segs = select_segments(transcript, use_llm and LLM_AVAILABLE
|
|
|
|
|
|
|
| 252 |
|
| 253 |
tree = ET.parse(premiere_xml_file.name)
|
| 254 |
tree = edit_sequence_with_segments(tree, segs)
|
|
@@ -257,30 +285,86 @@ def process_xml_and_transcript(premiere_xml_file, transcript_txt_file, use_llm):
|
|
| 257 |
out_path = os.path.join(OUTPUT_DIR, f"{base}_EDITADO.xml")
|
| 258 |
tree.write(out_path, encoding="utf-8", xml_declaration=True)
|
| 259 |
|
| 260 |
-
resumo = "
|
| 261 |
for i, s in enumerate(segs, 1):
|
| 262 |
-
|
|
|
|
|
|
|
| 263 |
|
| 264 |
-
status = f"LLM disponível: {LLM_AVAILABLE} | LLM
|
| 265 |
return resumo, out_path, status
|
| 266 |
|
| 267 |
-
with gr.Blocks() as demo:
|
| 268 |
-
gr.Markdown("# Agente de Edição XML para Premiere (
|
| 269 |
-
gr.Markdown("
|
| 270 |
-
|
| 271 |
-
|
| 272 |
with gr.Row():
|
| 273 |
-
|
| 274 |
-
|
| 275 |
-
|
| 276 |
-
|
| 277 |
-
|
| 278 |
-
|
| 279 |
-
|
| 280 |
-
|
| 281 |
-
|
| 282 |
-
|
| 283 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 284 |
|
| 285 |
if __name__ == "__main__":
|
| 286 |
-
demo.launch()
|
|
|
|
|
|
|
| 1 |
import os
|
| 2 |
import re
|
| 3 |
import xml.etree.ElementTree as ET
|
|
|
|
| 6 |
import gradio as gr
|
| 7 |
|
| 8 |
# Optional LLM (Gemini)
|
| 9 |
+
USE_LLM_DEFAULT = True
|
| 10 |
GEMINI_API_KEY = os.getenv("GEMINI_API_KEY", "").strip()
|
| 11 |
|
| 12 |
LLM_AVAILABLE = False
|
|
|
|
| 58 |
def parse_transcript(txt: str) -> List[Segment]:
|
| 59 |
lines = [l.strip() for l in txt.splitlines() if l.strip()]
|
| 60 |
results: List[Segment] = []
|
| 61 |
+
pat_range = re.compile(r"^\[?\s*(\d{2}:\d{2}:\d{2}[:;]\d{2})\s*[-—]\s*(\d{2}:\d{2}:\d{2}[:;]\d{2})\s*\]?\s+(.*)$")
|
| 62 |
pat_point = re.compile(r"^(\d{2}:\d{2}:\d{2}[:;]\d{2})\s+(.*)$")
|
| 63 |
for l in lines:
|
| 64 |
m = pat_range.match(l)
|
|
|
|
| 77 |
s, text = m.groups()
|
| 78 |
try:
|
| 79 |
s_f = parse_timecode_to_frames(s)
|
| 80 |
+
e_f = s_f + 4*FPS
|
| 81 |
e = frames_to_timecode(e_f)
|
| 82 |
results.append(Segment(s, e, s_f, e_f, text, 0.0))
|
| 83 |
except Exception:
|
| 84 |
continue
|
| 85 |
return results
|
| 86 |
|
| 87 |
+
def keyword_score(text: str, custom_keywords: str = "", weight_emotion: float = 2.0,
|
| 88 |
+
weight_break: float = 1.5, weight_learn: float = 1.2, weight_viral: float = 1.0) -> float:
|
| 89 |
t = text.lower()
|
| 90 |
kw_emotion = ["medo", "coragem", "raiva", "chorei", "feliz", "triste", "emocion", "culpa", "vergonha", "orgulho"]
|
| 91 |
kw_break = ["nunca", "de repente", "contraintuitivo", "ninguém te conta", "parei", "decidi", "quebrei", "virada"]
|
|
|
|
| 93 |
kw_viral = ["segredo", "verdade", "por trás", "3 passos", "passo a passo", "como eu", "ninguém fala"]
|
| 94 |
|
| 95 |
score = 0.0
|
| 96 |
+
for kw in kw_emotion: score += weight_emotion if kw in t else 0.0
|
| 97 |
+
for kw in kw_break: score += weight_break if kw in t else 0.0
|
| 98 |
+
for kw in kw_learn: score += weight_learn if kw in t else 0.0
|
| 99 |
+
for kw in kw_viral: score += weight_viral if kw in t else 0.0
|
| 100 |
+
|
| 101 |
+
# Custom keywords
|
| 102 |
+
if custom_keywords.strip():
|
| 103 |
+
custom_kw_list = [kw.strip().lower() for kw in custom_keywords.split(",") if kw.strip()]
|
| 104 |
+
for kw in custom_kw_list:
|
| 105 |
+
score += 3.0 if kw in t else 0.0
|
| 106 |
+
|
| 107 |
score += 0.2 * text.count("!")
|
| 108 |
score += 0.0005 * len(text)
|
| 109 |
return score
|
| 110 |
|
| 111 |
+
def llm_rank_segments(candidates: List[Segment], num_segments: int, custom_instructions: str = "") -> List[Segment]:
|
| 112 |
+
"""Ask the LLM to pick segments based on criteria."""
|
| 113 |
if not LLM_AVAILABLE:
|
| 114 |
+
return candidates[:num_segments]
|
| 115 |
+
|
| 116 |
sample = "\n".join([f"{i}. [{c.start_tc}-{c.end_tc}] {c.text[:300]}" for i, c in enumerate(candidates)])
|
| 117 |
+
|
| 118 |
+
base_prompt = (
|
| 119 |
+
f"Você é um editor profissional. Selecione exatamente {num_segments} trechos mais fortes "
|
| 120 |
+
"pela emoção, quebra de expectativa e aprendizado, mantendo uma mini-narrativa coerente.\n\n"
|
| 121 |
)
|
| 122 |
+
|
| 123 |
+
if custom_instructions.strip():
|
| 124 |
+
base_prompt += f"INSTRUÇÕES ADICIONAIS: {custom_instructions}\n\n"
|
| 125 |
+
|
| 126 |
+
base_prompt += "Responda apenas com índices (0-based) separados por vírgula.\n\n" + sample
|
| 127 |
+
|
| 128 |
try:
|
| 129 |
+
r = LLM.generate_content(base_prompt, generation_config={"temperature": 0.2})
|
| 130 |
txt = (r.text or "").strip()
|
| 131 |
idxs = [int(x) for x in re.findall(r"\d+", txt)]
|
| 132 |
idxs = [i for i in idxs if 0 <= i < len(candidates)]
|
| 133 |
+
if len(idxs) >= num_segments:
|
| 134 |
+
return [candidates[i] for i in idxs[:num_segments]]
|
| 135 |
+
elif len(idxs) > 0:
|
| 136 |
return [candidates[i] for i in idxs]
|
| 137 |
+
except Exception as e:
|
| 138 |
+
print(f"Erro no LLM: {e}")
|
| 139 |
+
|
| 140 |
+
return candidates[:num_segments]
|
| 141 |
+
|
| 142 |
+
def select_segments(transcript_txt: str, use_llm: bool, num_segments: int,
|
| 143 |
+
custom_keywords: str, custom_instructions: str,
|
| 144 |
+
weight_emotion: float, weight_break: float,
|
| 145 |
+
weight_learn: float, weight_viral: float) -> List[Segment]:
|
| 146 |
segs = parse_transcript(transcript_txt)
|
| 147 |
if not segs:
|
| 148 |
raise ValueError("Nenhum trecho válido encontrado na transcrição.")
|
| 149 |
+
|
| 150 |
for s in segs:
|
| 151 |
+
s.score = keyword_score(s.text, custom_keywords, weight_emotion, weight_break, weight_learn, weight_viral)
|
| 152 |
+
|
| 153 |
segs.sort(key=lambda x: x.score, reverse=True)
|
| 154 |
+
top = segs[:min(20, len(segs))]
|
| 155 |
+
|
| 156 |
if use_llm and LLM_AVAILABLE:
|
| 157 |
+
ranked = llm_rank_segments(top, num_segments, custom_instructions)
|
| 158 |
+
return ranked
|
| 159 |
+
|
| 160 |
+
return top[:num_segments]
|
| 161 |
|
| 162 |
# ---- XML editing ----
|
| 163 |
def get_sequence(root: ET.Element) -> ET.Element:
|
|
|
|
| 265 |
return tree
|
| 266 |
|
| 267 |
# ---- Gradio app ----
|
| 268 |
+
def process_xml_and_transcript(premiere_xml_file, transcript_txt_file, use_llm,
|
| 269 |
+
num_segments, custom_keywords, custom_instructions,
|
| 270 |
+
weight_emotion, weight_break, weight_learn, weight_viral):
|
| 271 |
if premiere_xml_file is None or transcript_txt_file is None:
|
| 272 |
return "Envie o XML do Premiere e a transcrição em .txt.", None, f"LLM disponível: {LLM_AVAILABLE}"
|
| 273 |
+
|
| 274 |
with open(transcript_txt_file.name, "r", encoding="utf-8") as f:
|
| 275 |
transcript = f.read()
|
| 276 |
|
| 277 |
+
segs = select_segments(transcript, use_llm and LLM_AVAILABLE, num_segments,
|
| 278 |
+
custom_keywords, custom_instructions,
|
| 279 |
+
weight_emotion, weight_break, weight_learn, weight_viral)
|
| 280 |
|
| 281 |
tree = ET.parse(premiere_xml_file.name)
|
| 282 |
tree = edit_sequence_with_segments(tree, segs)
|
|
|
|
| 285 |
out_path = os.path.join(OUTPUT_DIR, f"{base}_EDITADO.xml")
|
| 286 |
tree.write(out_path, encoding="utf-8", xml_declaration=True)
|
| 287 |
|
| 288 |
+
resumo = f"✂️ {len(segs)} cortes aplicados (24 fps):\n\n"
|
| 289 |
for i, s in enumerate(segs, 1):
|
| 290 |
+
dur_sec = (s.end_f - s.start_f) / FPS
|
| 291 |
+
resumo += f"{i}. {s.start_tc} → {s.end_tc} ({dur_sec:.1f}s)\n"
|
| 292 |
+
resumo += f" Score: {s.score:.1f} | {s.text[:150]}\n\n"
|
| 293 |
|
| 294 |
+
status = f"✓ LLM disponível: {LLM_AVAILABLE} | LLM usado: {use_llm and LLM_AVAILABLE}"
|
| 295 |
return resumo, out_path, status
|
| 296 |
|
| 297 |
+
with gr.Blocks(theme=gr.themes.Soft()) as demo:
|
| 298 |
+
gr.Markdown("# 🎬 Agente de Edição XML para Premiere (Controles Avançados)")
|
| 299 |
+
gr.Markdown("Edite sua sequência do Premiere com controle total sobre a seleção de trechos.")
|
| 300 |
+
|
|
|
|
| 301 |
with gr.Row():
|
| 302 |
+
with gr.Column():
|
| 303 |
+
xml_in = gr.File(label="📁 XML da sequência (FCP XML)", file_types=[".xml"])
|
| 304 |
+
txt_in = gr.File(label="📄 Transcrição (.txt) com timecodes", file_types=[".txt"])
|
| 305 |
+
|
| 306 |
+
with gr.Column():
|
| 307 |
+
gr.Markdown("### ⚙️ Configurações")
|
| 308 |
+
use_llm = gr.Checkbox(
|
| 309 |
+
label="🤖 Usar LLM (Gemini) para seleção semântica",
|
| 310 |
+
value=USE_LLM_DEFAULT and LLM_AVAILABLE,
|
| 311 |
+
info="Usa IA para escolher os melhores trechos narrativamente"
|
| 312 |
+
)
|
| 313 |
+
num_segments = gr.Slider(
|
| 314 |
+
minimum=2, maximum=10, step=1, value=5,
|
| 315 |
+
label="📊 Número de segmentos a selecionar",
|
| 316 |
+
info="Quantos trechos incluir no vídeo final"
|
| 317 |
+
)
|
| 318 |
+
|
| 319 |
+
with gr.Accordion("🎯 Palavras-chave Personalizadas", open=False):
|
| 320 |
+
custom_keywords = gr.Textbox(
|
| 321 |
+
label="Adicione palavras-chave importantes (separadas por vírgula)",
|
| 322 |
+
placeholder="Exemplo: transformação, resultado, método, estratégia",
|
| 323 |
+
info="Trechos com essas palavras terão prioridade máxima (peso 3.0)"
|
| 324 |
+
)
|
| 325 |
+
|
| 326 |
+
with gr.Accordion("📝 Instruções em Texto Livre para o LLM", open=False):
|
| 327 |
+
custom_instructions = gr.Textbox(
|
| 328 |
+
label="Instruções adicionais para o LLM",
|
| 329 |
+
placeholder="Exemplo: Prefira trechos que mostrem resultados concretos e evite introduções longas",
|
| 330 |
+
lines=3,
|
| 331 |
+
info="Só funciona se o LLM estiver ativado"
|
| 332 |
+
)
|
| 333 |
+
|
| 334 |
+
with gr.Accordion("⚖️ Ajuste Fino dos Pesos de Pontuação", open=False):
|
| 335 |
+
gr.Markdown("Ajuste a importância de cada categoria na pontuação heurística:")
|
| 336 |
+
with gr.Row():
|
| 337 |
+
weight_emotion = gr.Slider(0, 5, value=2.0, step=0.1, label="Emoção")
|
| 338 |
+
weight_break = gr.Slider(0, 5, value=1.5, step=0.1, label="Quebra de expectativa")
|
| 339 |
+
with gr.Row():
|
| 340 |
+
weight_learn = gr.Slider(0, 5, value=1.2, step=0.1, label="Aprendizado")
|
| 341 |
+
weight_viral = gr.Slider(0, 5, value=1.0, step=0.1, label="Viralização")
|
| 342 |
+
|
| 343 |
+
run_btn = gr.Button("🚀 Processar e Gerar XML Editado", variant="primary", size="lg")
|
| 344 |
+
|
| 345 |
+
gr.Markdown("---")
|
| 346 |
+
|
| 347 |
+
with gr.Row():
|
| 348 |
+
with gr.Column(scale=2):
|
| 349 |
+
resumo_out = gr.Textbox(label="📋 Resumo dos cortes aplicados", lines=15)
|
| 350 |
+
with gr.Column(scale=1):
|
| 351 |
+
status_out = gr.Textbox(label="ℹ️ Status", interactive=False)
|
| 352 |
+
file_out = gr.File(label="💾 Download do XML Editado")
|
| 353 |
+
|
| 354 |
+
run_btn.click(
|
| 355 |
+
process_xml_and_transcript,
|
| 356 |
+
inputs=[xml_in, txt_in, use_llm, num_segments, custom_keywords,
|
| 357 |
+
custom_instructions, weight_emotion, weight_break, weight_learn, weight_viral],
|
| 358 |
+
outputs=[resumo_out, file_out, status_out]
|
| 359 |
+
)
|
| 360 |
+
|
| 361 |
+
gr.Markdown("""
|
| 362 |
+
### 💡 Dicas de uso:
|
| 363 |
+
- **Modo Heurístico**: Desative o LLM e ajuste os pesos para controle total baseado em palavras-chave
|
| 364 |
+
- **Modo LLM**: Ative o LLM e use as instruções em texto livre para guiar a seleção semanticamente
|
| 365 |
+
- **Híbrido**: Combine palavras-chave personalizadas + instruções LLM para máximo controle
|
| 366 |
+
- **Palavras-chave**: Adicione termos específicos do seu nicho que devem ter alta prioridade
|
| 367 |
+
""")
|
| 368 |
|
| 369 |
if __name__ == "__main__":
|
| 370 |
+
demo.launch()
|