- Notifications
You must be signed in to change notification settings - Fork0
A python wrapper for speech feature extractoin
License
NotificationsYou must be signed in to change notification settings
dhchenx/speech-feature-kit
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
A Python wrapper for convenient speech feature extraction
pipinstallspeech-features-kit
- MFCC feature analysis
- Volume analysis
- Emotion analysis
fromspeech_features_kit.Emotion.speech_toolkitimportSpeechEmotionToolkit# set the path of pre-trained model for speech emotion model# the used model here is optimized for Chinese speech; however, it is possible you can train your own model.speech_kit=SpeechEmotionToolkit()# load the modelspeech_kit.load()# obtain emotion list with timestamp given an audio filelist_emo,list_timestamp=speech_kit.get_emotion_list_by_blocks(audio_file="../data/english.wav",num_sec_each_file=1)# print the list of emotion over timestampprint("Time interval\tEmotion")foridx,einenumerate(list_emo):print(list_timestamp[idx],"\t",e)
Other functions please see the examples folder!