1a91c19af9
whisper : perform entropy check only when we have at least 32 tokens ( #412 )
2 years ago
f583e2d2f5
main : we had accidentally disabled the temperature fallback .. ( #291 )
2 years ago
206fc93396
whisper.wasm : add small and small.en models
2 years ago
a6cf6f4c4a
bench : minor fixes
2 years ago
472a473fd1
main : add an option to accept optional output filenames ( #424 )
...
* Add an option to accept optional output filenames
* Format the file
Co-authored-by: Chia-Hsiang Cheng <gary.chiahsiang.cheng@gmail.com>
2 years ago
9ba66c2fad
stream : fix handling of --step == --length ( #416 )
2 years ago
1ccb8a46a5
bench : fix Windows linkage by moving ggml benches in whisper lib ..
2 years ago
1290fc6457
bench : add memcpy and ggml_mul_mat benchmarks
2 years ago
49b529ba74
whisper.android : add support for loading directly from asset in C ( #415 )
2 years ago
8088a977af
whisper : fix possible uninitialized variables ( #291 )
2 years ago
c9aeb33676
stream : fix --keep_context argument to be used correctly ( #354 )
2 years ago
4a3f0d3fe9
go : remove sample_best and sample_timestamp bindings ( #409 )
2 years ago
874bde887e
Update README.md
2 years ago
8738427dd6
cmake : bump version to 1.1.0
2 years ago
c3991bbb24
Update README.md
2 years ago
00ea21668b
whisper : account speed_up flag for short audio ( close #405 )
2 years ago
0b85e8c401
Update README.md
2 years ago
fafd78945d
bench.wasm : print system info
2 years ago
8de452c18b
Improve decoding ( #291 )
...
* whisper : prepare infra for new decoding strategies
* whisper : apply logit filters and compute logprobs
* whisper : add whisper_get_logits()
* whisper : separate self and cross attention memory
Initial step needed for supporting parallel decoders
* whisper : move probs_id buffer to whisper_context
* whisper : refactor kv cache into separate struct
* whisper : move self-attention kv cache to whisper_decoder
* whisper : wip decoding parameters + strategies
* whisper : wip decoding parameters + strategies (part 2)
* whisper : wip decoding parameters + strategies (part 3)
* whisper : wip decoding parameters + strategies (part 4)
* whisper : fix prompt_past update to not include prompt_init
* whisper : temperature + best_of support
* whisper : support for compression_ration_threshold
We actually use entropy, but it is similar
* command : fix example to use logits instead of obsolete probs
* whisper : handle empty sequence ranking
* whisper : add WHISPER_DEBUG + diagnostic prints + new main args
* whisper : minor fixes
* whisper : add beam-search support
* whisper : bug fix when there no previous context
* whisper : add comments
* stream : disable temperature fallback
For real-time processing, we always want a single decoder running at T=0
* whisper.swiftui : update example - fix paths + add empty folders
2 years ago
a6dbd9188b
stream : fix a bug that inserted a lot of empty audio at the start
...
The quality was terrible due to this
2 years ago
4ef3398e8f
ggml : remove obsolete zeroing + comment fixes ( #390 )
2 years ago
5e9f33596f
readme : clarify main and stream usage ( #391 )
...
Give an example of ./main that uses a sample file that's already there, and make the stream example clarify you need `make stream`
2 years ago
8d7b29cedd
ggml : correct behaviour of ggml_vec_sum_f32 ( #390 )
2 years ago
08dc705a69
whisper : fix sample_to_timestamp calculation with 64 bit precision to avoid overflow ( #388 )
...
* Do calculation with 64 bit precision to avoid overflow
* Update whisper.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2 years ago
1512545149
whisper : add loader class to allow loading from buffer and others ( #353 )
...
* whisper : add loader to allow loading from other than file
* whisper : rename whisper_init to whisper_init_from_file
* whisper : add whisper_init_from_buffer
* android : Delete local.properties
* android : load models directly from assets
* whisper : adding <stddef.h> needed for size_t + code style
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2 years ago
52a3e0c92a
ggml : improve vec_dot_f16 unrolling in flash_attn_f16
2 years ago
d1ea1220ff
command : clean-up / refactoring / formatting ( #383 )
2 years ago
9c4a1522f6
command : always-prompt mode ( #383 )
2 years ago
f078a6f20e
go : adding features to the go-whisper example, go ci, etc ( #384 )
...
* Updated bindings so they can be used in third pary packages.
* Updated makefiles to set FMA flag on optionally, for xeon E5 on Darwin
* Added test script
* Changes for examples
* Reverted
* Made the NewContext method private
2 years ago
f30b5d322c
ggml : fix bug in new soft max computation
2 years ago
44efbf7ff1
cmake : add -Wno-unused-function + update whisper.js
2 years ago
d347a59a5f
ggml : when using BLAS start only 1 CPU thread
2 years ago
6394c906af
ggml : fix running tasks with variable number of threads
2 years ago
74ffa14e1d
ggml : unroll ggml_vec_dot_f16 in ggml_compute_forward_flash_attn_f16
2 years ago
65fdcbbbbb
whisper : revert accidental MB change
2 years ago
d61d55cd4b
ggml : speed-up soft max via Accelerate + unroll
2 years ago
d51fc3ee0a
ggml : use vDSP_sve and vDSP_maxv from Accelerate
2 years ago
f82a7dd019
ggml : make gcc happy (minor)
2 years ago
87dd4a3081
talk.wasm : bump memory usage + update whisper.js
2 years ago
41e05c6b1b
cmake : support AVX2 in Windows better ( #381 )
2 years ago
fa379cb22a
Revert "tmp"
...
This reverts commit 1652965529
2 years ago
322f4e6c4e
go : bindings updated so they can be used in third party packages. ( #379 )
...
* Updated bindings so they can be used in third pary packages.
* Updated makefiles to set FMA flag on optionally, for xeon E5 on Darwin
2 years ago
1652965529
tmp
2 years ago
6042c7a3be
cmake : change min required version to 3.0 ( #351 )
...
We increase the min version only when want to use particular
functionality that is available in the newer version
2 years ago
6b351bb669
command : add "guided-mode" video demo in the README.md
2 years ago
a62170c656
ggml : add SSE3 and fp16 conversion lookup table ( #368 )
...
* Improves WASM performance:
On MacBook M1 Pro, I observe 25% faster using Firefox and 35% faster using Chrome
* Add support for SSE3 SIMD
* Add SSE3 to system information
* Add Imath support for fp16-fp32 conversions
* Add Imath to system information
* Wrap Imath calls to avoid static function warnings
* Drop Imath; Add lookup table for f16 -> f32 conversions
* Remove TODO comments
* Update SSE3 to new macro arguments
* Correct updated macro definitions
* Prefer static inline where possible
* ggml : static inlines + add public f16 <-> f32 conversions
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2 years ago
1944e7c33e
whisper : document POWER VSX support
2 years ago
49a8dd6732
ggml : reorganize POWER9 ppc64le SIMD code
2 years ago
8c7f642286
ggml : change f16 load and store macro arguments
2 years ago
ad2a4ffa03
whisper : do not use F16 tensors when in F32 mode ( #369 )
2 years ago
Georgi Gerganov