Skip to content

FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.

code update

维石2313a6217afb
diff --git a/funclip/introduction.py b/funclip/introduction.py
new file mode 100644
index 0000000..01d235d
--- /dev/null
+++ b/funclip/introduction.py
@@ -0,0 +1,30 @@
+top_md_1 = ("""
+ 基于阿里巴巴通义实验室自研SeACo-Paraformer-长音频版的语音识别、端点检测、标点预测、时间戳功能、角色区分、热词定制化功能
+
+ 准确识别,自由复制所需段落,或者设置说话人标识,一键裁剪、添加字幕
+
+ * Step1: 上传视频或音频文件(或使用下方的用例体验),点击 **<font color="#f7802b">识别</font>** 按钮
+ * Step2: 复制识别结果中所需的文字至右上方,或者右设置说话人标识,设置偏移与字幕配置(可选)
+ * Step3: 点击 **<font color="#f7802b">裁剪</font>** 按钮或 **<font color="#f7802b">裁剪并添加字幕</font>** 按钮获得结果
+ """)
+
+top_md_2 = ("""
+ 受到网络传输与服务资源的限制,用于体验的视频最好大小在40mb以下
+ 过大的视频可以尝试分离音轨使用音频剪辑,或 **<font color="#1785c4">通过源代码将您的ClipVideo服务部署在本地(推荐)</font>** :
+ <div align="center">
+ <div style="display:flex; gap: 0.25rem;" align="center">
+ FunASR_APP: <a href='https://github.com/alibaba/funasr-app'><img src='https://img.shields.io/badge/Github-Code-blue'></a>
+ 🌟支持我们: <a href='https://github.com/alibaba/funasr-app/stargazers'><img src='https://img.shields.io/github/stars/alibaba/funasr-app.svg?style=social'></a>
+ </div>
+ </div>
+ """)
+
+top_md_3 = ("""访问FunASR项目与论文能够帮助您深入了解ParaClipper中所使用的语音处理相关模型:
+ <div align="center">
+ <div style="display:flex; gap: 0.25rem;" align="center">
+ FunASR: <a href='https://github.com/alibaba-damo-academy/FunASR'><img src='https://img.shields.io/badge/Github-Code-blue'></a>
+ FunASR Paper: <a href="https://arxiv.org/abs/2305.11013"><img src="https://img.shields.io/badge/Arxiv-2305.11013-orange"></a>
+ 🌟Star FunASR: <a href='https://github.com/alibaba-damo-academy/FunASR/stargazers'><img src='https://img.shields.io/github/stars/alibaba-damo-academy/FunASR.svg?style=social'></a>
+ </div>
+ </div>
+ """)
diff --git a/funclip/launch.py b/funclip/launch.py
index ea67d30..6daf244 100644
--- a/funclip/launch.py
+++ b/funclip/launch.py
@@ -1,19 +1,15 @@
import gradio as gr
from funasr import AutoModel
from videoclipper import VideoClipper
+from introduction import top_md_1, top_md_2, top_md_3
if __name__ == "__main__":
-
funasr_model = AutoModel(model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
- model_revision="v2.0.4",
- vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
- vad_model_revision="v2.0.4",
- punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
- punc_model_revision="v2.0.4",
- spk_model="damo/speech_campplus_sv_zh-cn_16k-common",
- spk_model_revision="v2.0.2",
- )
+ vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+ punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
+ spk_model="damo/speech_campplus_sv_zh-cn_16k-common",
+ )
audio_clipper = VideoClipper(funasr_model)
def audio_recog(audio_input, sd_switch, hotwords):
@@ -45,40 +41,8 @@ if __name__ == "__main__":
(sr, res_audio), message, clip_srt = audio_clipper.clip(dest_text, start_ost, end_ost, audio_state, dest_spk=video_spk_input)
return None, (sr, res_audio), message, clip_srt
- top_md_1 = ("""
- 基于阿里巴巴通义实验室自研SeACo-Paraformer-长音频版的语音识别、端点检测、标点预测、时间戳功能、角色区分、热词定制化功能
-
- 准确识别,自由复制所需段落,或者设置说话人标识,一键裁剪、添加字幕
-
- * Step1: 上传视频或音频文件(或使用下方的用例体验),点击 **<font color="#f7802b">识别</font>** 按钮
- * Step2: 复制识别结果中所需的文字至右上方,或者右设置说话人标识,设置偏移与字幕配置(可选)
- * Step3: 点击 **<font color="#f7802b">裁剪</font>** 按钮或 **<font color="#f7802b">裁剪并添加字幕</font>** 按钮获得结果
- """)
-
- top_md_2 = ("""
- 受到网络传输与服务资源的限制,用于体验的视频最好大小在40mb以下
- 过大的视频可以尝试分离音轨使用音频剪辑,或 **<font color="#1785c4">通过源代码将您的ClipVideo服务部署在本地(推荐)</font>** :
- <div align="center">
- <div style="display:flex; gap: 0.25rem;" align="center">
- FunASR_APP: <a href='https://github.com/alibaba/funasr-app'><img src='https://img.shields.io/badge/Github-Code-blue'></a>
- 🌟支持我们: <a href='https://github.com/alibaba/funasr-app/stargazers'><img src='https://img.shields.io/github/stars/alibaba/funasr-app.svg?style=social'></a>
- </div>
- </div>
- """)
-
- top_md_3 = ("""访问FunASR项目与论文能够帮助您深入了解ParaClipper中所使用的语音处理相关模型:
- <div align="center">
- <div style="display:flex; gap: 0.25rem;" align="center">
- FunASR: <a href='https://github.com/alibaba-damo-academy/FunASR'><img src='https://img.shields.io/badge/Github-Code-blue'></a>
- FunASR Paper: <a href="https://arxiv.org/abs/2305.11013"><img src="https://img.shields.io/badge/Arxiv-2305.11013-orange"></a>
- 🌟Star FunASR: <a href='https://github.com/alibaba-damo-academy/FunASR/stargazers'><img src='https://img.shields.io/github/stars/alibaba-damo-academy/FunASR.svg?style=social'></a>
- </div>
- </div>
- """)
-
# gradio interface
with gr.Blocks() as demo:
- #gr.Image("./examples/guide.png", show_label=False)
gr.Markdown(top_md_1)
gr.Markdown(top_md_2)
gr.Markdown(top_md_3)
diff --git a/funclip/argparse_tools.py b/funclip/utils/argparse_tools.py
similarity index 100%
rename from funclip/argparse_tools.py
rename to funclip/utils/argparse_tools.py
diff --git a/funclip/subtitle_utils.py b/funclip/utils/subtitle_utils.py
similarity index 100%
rename from funclip/subtitle_utils.py
rename to funclip/utils/subtitle_utils.py
diff --git a/funclip/trans_utils.py b/funclip/utils/trans_utils.py
similarity index 100%
rename from funclip/trans_utils.py
rename to funclip/utils/trans_utils.py
diff --git a/funclip/videoclipper.py b/funclip/videoclipper.py
index f61f786..2ff0199 100644
--- a/funclip/videoclipper.py
+++ b/funclip/videoclipper.py
@@ -10,9 +10,9 @@ import soundfile as sf
import moviepy.editor as mpy
from moviepy.editor import *
from moviepy.video.tools.subtitles import SubtitlesClip
-from subtitle_utils import generate_srt, generate_srt_clip
-from argparse_tools import ArgumentParser, get_commandline_args
-from trans_utils import pre_proc, proc, write_state, load_state, proc_spk, convert_pcm_to_float
+from utils.subtitle_utils import generate_srt, generate_srt_clip
+from utils.argparse_tools import ArgumentParser, get_commandline_args
+from utils.trans_utils import pre_proc, proc, write_state, load_state, proc_spk, convert_pcm_to_float
class VideoClipper():