Quentin Fuxa
|
3bd2122eb4
|
0.2.8 : only the decoder of whisper is loaded in memory when a different encoder is used
|
2025-09-02 21:12:25 +02:00 |
|
Quentin Fuxa
|
50b0527858
|
update architecture
|
2025-09-01 21:24:12 +02:00 |
|
Quentin Fuxa
|
b0508fcf2c
|
mlx/fasterWhisper encoders are loaded once and shared in simulstreaming
|
2025-09-01 14:55:11 +02:00 |
|
Quentin Fuxa
|
d5008ed828
|
mlx/fasterWhisper encoders are loaded once and shared in simulstreaming
|
2025-09-01 12:33:19 +02:00 |
|
Quentin Fuxa
|
e14bbde77d
|
sortformer diar implementation v0
|
2025-08-19 17:02:55 +02:00 |
|
Quentin Fuxa
|
d098af3185
|
each SimulStreamingOnlineProcessor now contains PaddedAlignAttWhisper instance. SimulStreamingASR only contains loaded whisper model
|
2025-08-11 08:24:14 +02:00 |
|
Quentin Fuxa
|
bb6b9f4cb1
|
architecture diagram : available backends for whisper streaming & diarization
|
2025-08-03 12:25:36 +02:00 |
|
Quentin Fuxa
|
e40b5a3ea0
|
Update architecture diagram
|
2025-08-02 13:51:15 +02:00 |
|