124 lines
4.8 KiB
Python
124 lines
4.8 KiB
Python
import requests
|
|
import time
|
|
import argparse
|
|
import multiprocessing
|
|
import sys
|
|
import os
|
|
|
|
INGEST_URL = "https://emiapi.reynafamily.com/live-captions/ingest"
|
|
|
|
def post_with_retries(payload, timeout, max_attempts=3):
|
|
delay = 1
|
|
for attempt in range(1, max_attempts + 1):
|
|
try:
|
|
response = requests.post(INGEST_URL, json=payload, timeout=timeout)
|
|
if response.status_code == 200:
|
|
return True
|
|
print(f"[Distribute Error] {response.status_code} on attempt {attempt}/{max_attempts}.")
|
|
except Exception as exc:
|
|
print(f"[Distribute Error] {exc} on attempt {attempt}/{max_attempts}.")
|
|
if attempt < max_attempts:
|
|
time.sleep(delay)
|
|
delay = min(delay * 2, 5)
|
|
return False
|
|
|
|
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:
|
|
post_with_retries({"draft": draft_text}, timeout=2, max_attempts=2)
|
|
continue
|
|
|
|
# Finalized segment
|
|
speaker_label = payload.get('speaker')
|
|
speaker_prefix = f"[{speaker_label}]: " if speaker_label else ""
|
|
|
|
msg = f"[Final]: {speaker_prefix}{payload.get('original', '')}"
|
|
print(msg, flush=True)
|
|
log_debug(msg)
|
|
|
|
bridge_text = payload.get("en_bridge")
|
|
original_text = payload.get("original", "")
|
|
corrected_text = payload.get("corrected")
|
|
paragraph_text = payload.get("paragraph")
|
|
|
|
if bridge_text and bridge_text.strip() != original_text.strip():
|
|
bridge_msg = f"[EN-BRIDGE]: {speaker_prefix}{bridge_text}"
|
|
print(bridge_msg, flush=True)
|
|
log_debug(bridge_msg)
|
|
|
|
if payload.get("used_llm_line") and corrected_text and corrected_text.strip() != bridge_text.strip():
|
|
llm_line_msg = f"[LLM-LINE]: {speaker_prefix}{corrected_text}"
|
|
print(llm_line_msg, flush=True)
|
|
log_debug(llm_line_msg)
|
|
|
|
if payload.get("used_llm_paragraph") and paragraph_text:
|
|
print("", flush=True)
|
|
log_debug("")
|
|
llm_paragraph_msg = f"[LLM-PARAGRAPH]: {speaker_prefix}{paragraph_text}"
|
|
print(llm_paragraph_msg, flush=True)
|
|
log_debug(llm_paragraph_msg)
|
|
print("", flush=True)
|
|
log_debug("")
|
|
|
|
if payload.get("paragraph_fallback") and paragraph_text:
|
|
paragraph_msg = f"[PARAGRAPH]: {speaker_prefix}{paragraph_text}"
|
|
print(paragraph_msg, flush=True)
|
|
log_debug(paragraph_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:
|
|
success = post_with_retries(ingest_payload, timeout=5, max_attempts=3)
|
|
if not success:
|
|
log_debug(f"Dropped ingest payload after retries: {ingest_payload}")
|
|
|
|
except Exception as e:
|
|
print(f"[Distribute] Error: {e}")
|
|
|
|
if __name__ == "__main__":
|
|
import multiprocessing
|
|
run_distribution(multiprocessing.Queue(), argparse.Namespace())
|