search

snakers4 / silero-models

Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
Other
5.01k stars 316 forks source link

Fix tts example #167

Closed ghost closed 2 years ago

ghost commented 2 years ago

models.tts_models.get(lang) returns model names while model.speakers returns speaker names.

A user might make a mistake when trying to change the language/speaker, thinking e. g. "v3_en" is a speaker.

Example old output:

Available speakers for en: ['v3_en', 'v3_en_indic', 'lj_v2', 'lj_8khz', 'lj_16khz']

How it should be:

Available models for en: ['v3_en', 'v3_en_indic', 'lj_v2', 'lj_8khz', 'lj_16khz']