Quentin Fuxa a5503308c5 O(n) to O(1) for simulstreaming timestamp determination		2025-09-21 11:04:00 +02:00
..
whisper	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
__init__.py	refactor(simulstreaming): extract backend + online module into separate files from whisper streaming	2025-08-08 18:07:51 +02:00
backend.py	O(n) to O(1) for simulstreaming timestamp determination	2025-09-21 11:04:00 +02:00
beam.py	modify import paths in simul whisper backend so that it works in lib mode	2025-07-01 20:34:47 +02:00
config.py	audio_max_len to 30 -> 20, ffmpeg timeout 5 -> 20	2025-08-17 09:32:08 +02:00
eow_detection.py	modify import paths in simul whisper backend so that it works in lib mode	2025-07-01 20:34:47 +02:00
generation_progress.py	latest version of simulstreaming	2025-07-31 16:44:23 +02:00
license_simulstreaming.py	each SimulStreamingOnlineProcessor now contains PaddedAlignAttWhisper instance. SimulStreamingASR only contains loaded whisper model	2025-08-11 08:24:14 +02:00
mlx_encoder.py	mlx/fasterWhisper encoders are loaded once and shared in simulstreaming	2025-09-01 12:33:19 +02:00
simul_whisper.py	O(n) to O(1) for simulstreaming timestamp determination	2025-09-21 11:04:00 +02:00
token_buffer.py	modify import paths in simul whisper backend so that it works in lib mode	2025-07-01 20:34:47 +02:00