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.
31 lines
674 B
Python
31 lines
674 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-fast",
|
|
description="提取指定音轨并用 SenseVoice 快速转录。",
|
|
)
|
|
add_common_args(parser)
|
|
return parser
|
|
|
|
|
|
def main() -> None:
|
|
args = build_parser().parse_args()
|
|
run_pipeline(
|
|
args,
|
|
model_name="sensevoice",
|
|
config=REGULAR_MODEL_CONFIGS["sensevoice"],
|
|
suffix="sensevoice",
|
|
use_itn=True,
|
|
sensevoice=True,
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|