voice100 icon indicating copy to clipboard operation
voice100 copied to clipboard

verified publisher icon kaiidams
→

Metadata

Voice100 includes neural TTS/ASR models. Inference of Voice100 is low cost as its models are tiny and only depend on CNN without autoregression.

Results 2 voice100 issues
Sort by recently updated
recently updated
newest added

Speech to Speech

2 comment

For your looking-ahead inspiration: [speech_to_speech](https://github.com/pytorch/fairseq/blob/main/examples/speech_to_speech/README.md)

GeorgeS2019 avatar GeorgeS2019

Revisit `asr_en_phone_base-20230314`

`asr_en_phone_base-20230314` has 4 layer convolusion. Compare with 2 layer convolusion.

kaiidams avatar kaiidams

← Metadata

26
Stars
3
Forks
Watchers

Owner

verified publisher icon kaiidams

Metadata

Voice100 includes neural TTS/ASR models. Inference of Voice100 is low cost as its models are tiny and only depend on CNN without autoregression.

Back