Skip to content

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

bug fix

CodeLyokoscj8c9101febd47
diff --git a/funclip/videoclipper.py b/funclip/videoclipper.py
index 706ce1f..7e70651 100644
--- a/funclip/videoclipper.py
+++ b/funclip/videoclipper.py
@@ -25,6 +25,7 @@ class VideoClipper():
logging.warning("Initializing VideoClipper.")
self.funasr_model = funasr_model
self.GLOBAL_COUNT = 0
+ self.lang = "zh"
def recog(self, audio_input, sd_switch='no', state=None, hotwords="", output_dir=None):
if state is None:
@@ -337,10 +338,16 @@ def get_parser():
default=None,
help="Output file path"
)
+ parser.add_argument(
+ "--lang",
+ type=str,
+ default="zh",
+ help="Language choose"
+ )
return parser
-def runner(stage, file, sd_switch, output_dir, dest_text, dest_spk, start_ost, end_ost, output_file, config=None):
+def runner(stage, file, sd_switch, output_dir, dest_text, dest_spk, start_ost, end_ost, output_file, lang="zh", config=None):
audio_suffixs = ['.wav','.mp3','.aac','.m4a','.flac']
video_suffixs = ['.mp4','.avi','.mkv','.flv','.mov','.webm','.ts','.mpeg']
_,ext = os.path.splitext(file)
@@ -359,12 +366,20 @@ def runner(stage, file, sd_switch, output_dir, dest_text, dest_spk, start_ost, e
from funasr import AutoModel
# initialize funasr automodel
logging.warning("Initializing modelscope asr pipeline.")
- funasr_model = AutoModel(model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
- 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",
- )
+ if lang == "zh":
+ funasr_model = AutoModel(model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
+ 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",
+ )
+ elif lang == "en":
+ funasr_model = AutoModel(model="iic/speech_paraformer_asr-en-16k-vocab4199-pytorch",
+ 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)
+ audio_clipper.lang = lang
if mode == 'audio':
logging.warning("Recognizing audio file: {}".format(file))
wav, sr = librosa.load(file, sr=16000)