nite
a565382a52
A conversational video-editing planning assistant. Provides tools for: - Audio transcription via bundled funasr-script (Fun-ASR-Nano / SenseVoice) - On-demand clip extraction and frame sampling (ffmpeg, hardware-accelerated) - SQLite index to track all artifacts and avoid duplicate processing - Vision analysis guidance with binary-search-style frame sampling - Iterative Markdown-table edit plan output Agent-agnostic: no platform-specific tool names, works with any agent runtime. Dependencies checked at guidance level with OS package manager install hints.
38 lines
948 B
Python
38 lines
948 B
Python
from __future__ import annotations
|
|
|
|
import argparse
|
|
|
|
from funasr_common import REGULAR_MODEL_CONFIGS, add_common_args, run_pipeline
|
|
|
|
|
|
def build_parser() -> argparse.ArgumentParser:
|
|
parser = argparse.ArgumentParser(
|
|
prog="funasr-regular",
|
|
description="提取指定音轨并用常规 FunASR 管线转录（SenseVoice/Paraformer）。",
|
|
)
|
|
add_common_args(parser)
|
|
parser.add_argument(
|
|
"--model",
|
|
choices=sorted(REGULAR_MODEL_CONFIGS),
|
|
default="sensevoice",
|
|
help="常规 FunASR 模型，默认 sensevoice",
|
|
)
|
|
return parser
|
|
|
|
|
|
def main() -> None:
|
|
args = build_parser().parse_args()
|
|
config = REGULAR_MODEL_CONFIGS[args.model]
|
|
run_pipeline(
|
|
args,
|
|
model_name=args.model,
|
|
config=config,
|
|
suffix=args.model,
|
|
use_itn=args.model == "sensevoice",
|
|
sensevoice=args.model == "sensevoice",
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|