As of #1486, whisper.cpp uses a unified KV cache with KQ masking.
As a result, depending on their location in the batch,
identical sequences in a batch can have slightly different outputs
due to floating point rounding errors during reduction.
See the discussion in #1941 for more details.
The beam search code used "has identical sum of log probabilities"
as a shorthand for "is an identical token sequence". However, per above,
identical tokens do not necessarily result in identical probabilities.
Instead, explicitly compare on sequences.
This is linear in cost when they are identical,
but the lengths are always small and the comparisons are cheap.
This increases diversity during beam search.
This improves output quality for some short samples I've been working
with, at no detectable performance cost.
I haven't checked against larger corpuses.
Fixes#1941
All else being otherwise equal, this encourages the beam candidate
selection to re-use the same decoder, which slightly
reduces the cache size.
I wouldn't expect it to make much of a performance difference,
but it helps when debug printing the cache and beam.
Added as part of understanding #1941.
* Update whisper.h
add whisper_lang_fullstr to retrieve the full language name
* Update whisper.cpp
add whisper_lang_fullstr to return the full language name
* fullstr -> str_full
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* whisper : migrate to ggml-backend
* whisper : fix logit reading
* whisper : fix tensor allocation during load
* whisper : fix beam-search with CUDA
* whisper : free backends + fix compile warning
* whisper : print when CUDA is enabled
* whisper : fix CoreML
* make : clean-up
* talk : fix compile warning
* whisper : support ggml_conv with CUDA and Metal (#1473)
* ggml : add CUDA support for ggml_conv
* whisper : remove ggml_repeat for conv bias + single backend
* cuda : fix im2col kernel
* metal : add im2col support + mul mat-vec f16 x f16
* bench-all : add q4 models
* whisper : clean-up
* quantize-all : fix
* ggml : im2col opts
* whisper : avoid whisper_model_data wrapper
* whisper : add note that ggml_mul_mat_pad does not work with CUDA
* whisper : factor out graph compute in common function
* whisper : fixes
* whisper : fix UB with measure buffers
* whisper : try to fix the parallel whisper_state functionality (#1479)
* whisper : try to fix the parallel whisper_state functionality
* whisper : fix multi-state Metal
* whisper : free backend instances in whisper_state
* whisper : check state->ctx_metal not null
* whisper : add whisper_context_params { use_gpu }
* whisper : new API with params & deprecate old API
* examples : use no-gpu param && whisper_init_from_file_with_params
* whisper.objc : enable metal & disable on simulator
* whisper.swiftui, metal : enable metal & support load default.metallib
* whisper.android : use new API
* bindings : use new API
* addon.node : fix build & test
* bindings : updata java binding
* bindings : add missing whisper_context_default_params_by_ref WHISPER_API for java
* metal : use SWIFTPM_MODULE_BUNDLE for GGML_SWIFT and reuse library load
* metal : move bundle var into block
* metal : use SWIFT_PACKAGE instead of GGML_SWIFT
* style : minor updates
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.)
* metal : allow env metal variable to override resource path (#1415)
* Allow env variable to override resource path
* Update ggml-metal.m
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* sync : restore common / main from `master`
* sync : restore whisper from `master`
* talk-llama : update to latest llama.cpp
* ruby : fix build
* ggml : fix 32-bit ARM build
* ggml : fix MIN / MAX macro collisions + update ios bindings
* ggml : fix ifdefs and MIN / MAX again
* exampels : fix Obj-C and Swift examples
* ggml : fix 32-bit ARM compatibility
* ggml : one more attempt to fix 32-bit ARM compat
* whisper : fix support for larger graphs
---------
Co-authored-by: Chris Raethke <codesoda@users.noreply.github.com>
