Skip to content

SOTA Open Source TTS

fix(tools/whisper_asr): use example (#258)

WWWwf6622bfcb496
diff --git a/tools/whisper_asr.py b/tools/whisper_asr.py
index 5495953..08aa1c8 100644
--- a/tools/whisper_asr.py
+++ b/tools/whisper_asr.py
@@ -12,11 +12,11 @@ Directory structure:
------02.wav
------......
Use
-python tools/whisper_asr.py --audio_dir pre_data_root/SP_1 --save_dir data/SP_1
+python tools/whisper_asr.py --audio-dir pre_data_root/SP_1 --save-dir data/SP_1
to transcribe the first speaker.
Use
-python tools/whisper_asr.py --audio_dir pre_data_root/SP_2 --save_dir data/SP_2
+python tools/whisper_asr.py --audio-dir pre_data_root/SP_2 --save-dir data/SP_2
to transcribe the second speaker.
Note: Be aware of your audio sample rate, which defaults to 44.1kHz.