ALPACA-RTAW

Native output

ここに表示

Foreign output

Display here

Speech recognition

Recognize lang
Dictionary
Start

Speaker adaptation

Adapt target
Training
FileSave

OBS connection settings

IPAddr
Port
Password
Connect

Speech translate settings

GAS deploy key
Native lang
Foreign lang
Foreign lang 2
Test

Speech voice settings

Native voice
Volume
Pitch
Rate
Test
Foreign voice
Volume
Pitch
Rate
Foreign voice 2
Volume
Pitch
Rate
Test

OBS TextGDIPlus settings

Native source
Foreign source
Foreign source 2
Timeout
Subtitle limit (native)
Subtitle limit (foreign)
Subtitle scroll time

Overflow settings

Overflow start timeout
Overflow keep timeout
Overflow limit
Overflow resolution
Overflow native separator
Overflow foreign separator

OBS Replay settings

keyword - Save
keyword - Move
Replay scene

OBS Scene switch settings (β)

keyword - Move
keyword - Return
Move scene
Base scene

LiveLog settings

API key
Param1
Param2

Emotion settings

Key
Happy - Pitch
Happy - Rate
Happy - Prefix
Sad - Pitch
Sad - Rate
Sad - Prefix
Surprised - Pitch
Surprised - Rate
Surprised - Prefix
Angry - Pitch
Angry - Rate
Angry - Prefix
Fearful - Pitch
Fearful - Rate
Fearful - Prefix
Disgusted - Pitch
Disgusted - Rate
Disgusted - Prefix

これは何？

音声認識からリアルタイムで翻訳し、認識結果と翻訳結果を音声合成で読み上げます。

OBS連携することで、音声認識した文字列と翻訳した文字列をOBS上に表示できます。

使い方は Github 参照のこと。

v1.6.2
Github
Twitter