Overview
Since the v1.1.0 pre-release there have been several reports of improved transcription quality.
Together with my observations, I think we can declare version v1.1.1
as "stable".
There were actually a couple of bug-fixes implemented since v1.1.0
, so make sure to update to v1.1.1
for optimal results.
Another update is that the prototype for v1.2.0 is almost ready: #431
Initial results indicate that the memory usage can be reduced by a factor of 2-3 for the smaller models.
You can provide feedback in the existing v1.1.0 discussion.
What's Changed
Core ggml
/ whisper
whisper
: perform entropy check only when we have at least 32 tokens 1a91c19whisper
: fix condition for providing past prompt (critical) 78f1661
Bindings
go
: removesample_best
andsample_timestamp
bindings by @Trojan295 in #409
Examples
main
: re-enable temperature fallback f583e2dmain
: add an option to accept optional output filenames by @garychia in #424whisper.android
: use AssetManager for Android by @Digipom in #415whisper.wasm
: add small and small.en models 206fc93bench
: add memcpy and ggml_mul_mat benchmarks (experimental) 1290fc6
New Contributors
- @Trojan295 made their first contribution in #409
- @garychia made their first contribution in #424
Full Changelog: v1.1.0...v1.1.1