Pull requests · speechbrain/speechbrain
[Code from Samsung AI Cambridge] BESTOW streaming for speech-to-text translation
#3059
opened
Bump gitpython from 3.1.37 to 3.1.47 in /recipes/BinauralWSJ0Mix
dependencies
#3051
opened
fix: Decoder input tensor dimension error
#3049
opened
8 of 13 tasks
add markdown files for agentic models
#3048
opened
fix float columns being converted to string in from_csv
#3043
opened
Optimize minDCF memory footprint
#3037
opened
6 of 13 tasks
fix spectrogram drop mask staring position
#3036
opened
13 tasks
add mossformer2 training with Aishell1 mix
#3035
opened
13 tasks
Bump virtualenv from 20.31.2 to 20.36.1
dependencies
#3024
opened
Add Myst children speech recipe
recipes
#2997
opened
7 tasks done
Add type checking with PyRight to CI (from Samsung AI Center Cambridge)
#2901
opened
4 of 13 tasks
Tokotron: Tokenized TTS (lite version - minimal dependencies)
recipes
Add minimum segment length threshold to energy VAD to prevent processing short segments
#2776
opened
8 of 13 tasks
Tokotron: Tokenized TTS
enhancement
#2696
opened
6 of 13 tasks
Inference audio normalizer changes and use load_audio in more places
#2695
opened
13 tasks
Multi-Window Multi-Head Attention implementation for ASR transformer
#2675
opened
✨ Add SNAC
enhancement
#2568
opened
7 of 13 tasks
Modified conformer warmup
enhancement
#2566
opened
13 tasks