WIP

main.py

@@ -12,7 +12,9 @@ from typing import Callable
 
 import torch
 from asr import Asr, AsrRawResult
-from asr_filter import AsrFilter
+from asr_filter import AsrFilter, AsrFilterResult
+from asr_eventizer import AsrEventizer
+from windowizer import Windowizer
 
 from agent import Agent
 from utils import ffmpeg_split_video, ffmpeg_to_mp3
@@ -138,13 +140,36 @@ def on_asr_filter(current_step: Step, input_data: dict | None) -> tuple[Step | N
             return (Step.ASR_EVENTS, json.load(f))
     # bad request
     if input_data is None:
-        logging.error("Can'f filter raw ASR ouput without input_data")
+        logging.error("Can't filter raw ASR output without input_data")
         return (None, None)
     logging.info("Filtering raw ASR output...")
     filter = AsrFilter()
     result = filter.filter(AsrRawResult(**input_data))
     return (Step.ASR_EVENTS, result.model_dump(mode="json"))
 
+def on_asr_events(current_step: Step, input_data: dict | None) -> tuple[Step | None, dict | None]:
+    # do not filter if output file exists
+    if os.path.isfile(WORKFLOW_DATA[current_step][0]):
+        logging.info("Skipping ASR eventizing")
+        with open(WORKFLOW_DATA[current_step][0], "rb") as f:
+            return (Step.VIDEO_REFERENCES, json.load(f))
+    # bad request
+    if input_data is None:
+        logging.error("Can't create audio events without input_data")
+        return (None, None)
+    logging.info("Creating the agent")
+    agent = Agent(
+        model=ARGS.ai_model,
+        base_url=ARGS.ai_base_url,
+        api_key=ARGS.ai_api_key
+    )
+    logging.info("Creating the windowizer")
+    windowizer = Windowizer()
+    logging.info("Creating audio events...")
+    eventizer = AsrEventizer(agent, windowizer)
+    result = eventizer.eventize(AsrFilterResult(**input_data))
+    return (Step.VIDEO_REFERENCES, result.model_dump(mode="json"))
+
 #
 # Main
 #
@@ -152,7 +177,7 @@ WORKFLOW_DATA: dict[Step, tuple[str, Callable[[Step, dict | None], tuple[Step |
     Step.MEDIA_SEPARATION: ("audio.mp3", on_media_separation),
     Step.VOICE_RECOGNITION: ("asr_raw.json", on_voice_recognition),
     Step.ASR_FILTER: ("asr.json", on_asr_filter),
-    Step.ASR_EVENTS: ("audio_events.json", None),
+    Step.ASR_EVENTS: ("audio_events.json", on_asr_events),
     Step.VIDEO_REFERENCES: ("unresolved.json", None),
     Step.REFERENCE_RESOLVER: ("events.json", None),
     Step.STRUCTURE_BUILDER: ("structure.json", None),