SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
Paper
•
2110.07205
•
Published
•
1
SpeechT5
The SpeechT5 framework consists of a shared seq2seq and six modal-specific (speech/text) pre/post-nets that can address a few audio-related tasks.
-
microsoft/speecht5_tts
Text-to-Speech • Updated • 54.4k • 273Note Text-to-speech version of SpeechT5
-
Running ont4184👩🎤
SpeechT5 Speech Synthesis Demo
microsoft/speecht5_vc
Audio-to-Audio • Updated • 16.2k • 36Note Voice-conversion version of SpeechT5
-
82👩🎤
SpeechT5 Voice Conversion Demo
microsoft/speecht5_asr
Automatic Speech Recognition • Updated • 3.56k • 18Note Automatic-speech-recognition version of SpeechT5
-
33👩🎤
SpeechT5 Speech Recognition Demo
microsoft/speecht5_hifigan
Updated • 73.4k • 10Note SpeechT5 produces a spectrogram, this model converts it to a waveform