Adolfo Reyna
97 lines
3.7 KiB
Python
97 lines
3.7 KiB
Python
import requests
|
|
import time
|
|
import argparse
|
|
import multiprocessing
|
|
import sys
|
|
import os
|
|
|
|
INGEST_URL = "https://emiapi.reynafamily.com/live-captions/ingest"
|
|
|
|
def log_debug(message):
|
|
try:
|
|
with open("distribute_debug.log", "a") as f:
|
|
f.write(f"{time.strftime('%H:%M:%S')} {message}\n")
|
|
f.flush()
|
|
os.fsync(f.fileno())
|
|
except:
|
|
pass
|
|
|
|
def run_distribution(in_queue, args):
|
|
print("[Distribute] Starting distribution service...", flush=True)
|
|
log_debug("Starting distribution service...")
|
|
|
|
while True:
|
|
try:
|
|
payload = in_queue.get()
|
|
if payload is None: break
|
|
|
|
# Draft support
|
|
if "draft" in payload:
|
|
draft_text = payload["draft"]
|
|
sys.stdout.write(f"\r\033[K[DRAFT]: {draft_text}")
|
|
sys.stdout.flush()
|
|
if args.ingest:
|
|
try: requests.post(INGEST_URL, json={"draft": draft_text}, timeout=2)
|
|
except: pass
|
|
continue
|
|
|
|
# Finalized segment
|
|
speaker_label = payload.get('speaker')
|
|
speaker_prefix = f"[{speaker_label}]: " if speaker_label else ""
|
|
|
|
msg = f"\n[Final]: {speaker_prefix}{payload.get('original', '')}"
|
|
print(msg, flush=True)
|
|
log_debug(msg)
|
|
|
|
# Show LLM Refinement if available
|
|
refined = payload.get('paragraph') or payload.get('corrected')
|
|
if refined and refined.strip() != payload.get('original', '').strip():
|
|
llm_msg = f"[LLM]: {speaker_prefix}{refined}"
|
|
print(llm_msg, flush=True)
|
|
log_debug(llm_msg)
|
|
|
|
for lang in ["es", "fr", "ar", "en"]:
|
|
if payload.get(lang):
|
|
lang_msg = f"[{lang.upper()}]: {speaker_prefix}{payload[lang]}"
|
|
print(lang_msg, flush=True)
|
|
log_debug(lang_msg)
|
|
|
|
if args.ingest:
|
|
# Flat JSON Schema: Keep only what's needed for the server
|
|
ingest_payload = {
|
|
"original": payload.get("original"),
|
|
"speaker": payload.get("speaker"),
|
|
"ts": payload.get("ts")
|
|
}
|
|
has_any_translation = False
|
|
for lang in ["es", "fr", "ar", "en"]:
|
|
if payload.get(lang):
|
|
ingest_payload[lang] = payload[lang]
|
|
has_any_translation = True
|
|
|
|
# If only-translate-llm is on, ONLY send when we have a translation (paragraph-level)
|
|
should_send = True
|
|
if getattr(args, "only_translate_llm", False) and not has_any_translation:
|
|
should_send = False
|
|
|
|
if should_send:
|
|
delay, max_delay, success = 1, 15, False
|
|
while not success:
|
|
try:
|
|
response = requests.post(INGEST_URL, json=ingest_payload, timeout=5)
|
|
if response.status_code == 200: success = True
|
|
else: print(f"[Distribute Error] {response.status_code}. Retrying...")
|
|
except Exception as e:
|
|
print(f"[Distribute Error] {e}. Retrying...")
|
|
|
|
if not success:
|
|
time.sleep(delay)
|
|
delay = min(delay * 2, max_delay)
|
|
|
|
except Exception as e:
|
|
print(f"[Distribute] Error: {e}")
|
|
|
|
if __name__ == "__main__":
|
|
import multiprocessing
|
|
run_distribution(multiprocessing.Queue(), argparse.Namespace())
|