d83e47573b
whisper : add comments
3 years ago
6700cd57f7
whisper : bug fix when there no previous context
3 years ago
5548a1986f
whisper : add beam-search support
3 years ago
5e97f80fc5
whisper : minor fixes
3 years ago
c301a7942b
whisper : add WHISPER_DEBUG + diagnostic prints + new main args
3 years ago
c6a8a47039
whisper : handle empty sequence ranking
3 years ago
7ea1b736ec
command : fix example to use logits instead of obsolete probs
3 years ago
c67716faba
whisper : support for compression_ration_threshold
...
We actually use entropy, but it is similar
3 years ago
34c5110f59
whisper : temperature + best_of support
3 years ago
712bc4b960
whisper : fix prompt_past update to not include prompt_init
3 years ago
bd6e70b512
whisper : wip decoding parameters + strategies (part 4)
3 years ago
116dd67a15
whisper : wip decoding parameters + strategies (part 3)
3 years ago
3d723d0b82
whisper : wip decoding parameters + strategies (part 2)
3 years ago
9551d7fabd
whisper : wip decoding parameters + strategies
3 years ago
628843c60a
whisper : move self-attention kv cache to whisper_decoder
3 years ago
ee58108df8
whisper : refactor kv cache into separate struct
3 years ago
1163f266d2
whisper : move probs_id buffer to whisper_context
3 years ago
523e0494a6
whisper : separate self and cross attention memory
...
Initial step needed for supporting parallel decoders
3 years ago
21559537e2
whisper : add whisper_get_logits()
3 years ago
2d8d3724b8
whisper : apply logit filters and compute logprobs
3 years ago
abe104b80b
whisper : prepare infra for new decoding strategies
3 years ago
4ef3398e8f
ggml : remove obsolete zeroing + comment fixes ( #390 )
3 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`
3 years ago
8d7b29cedd
ggml : correct behaviour of ggml_vec_sum_f32 ( #390 )
3 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>
3 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>
3 years ago
52a3e0c92a
ggml : improve vec_dot_f16 unrolling in flash_attn_f16
3 years ago
d1ea1220ff
command : clean-up / refactoring / formatting ( #383 )
3 years ago
9c4a1522f6
command : always-prompt mode ( #383 )
3 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
3 years ago
f30b5d322c
ggml : fix bug in new soft max computation
3 years ago
44efbf7ff1
cmake : add -Wno-unused-function + update whisper.js
3 years ago
d347a59a5f
ggml : when using BLAS start only 1 CPU thread
3 years ago
6394c906af
ggml : fix running tasks with variable number of threads
3 years ago
74ffa14e1d
ggml : unroll ggml_vec_dot_f16 in ggml_compute_forward_flash_attn_f16
3 years ago
65fdcbbbbb
whisper : revert accidental MB change
3 years ago
d61d55cd4b
ggml : speed-up soft max via Accelerate + unroll
3 years ago
d51fc3ee0a
ggml : use vDSP_sve and vDSP_maxv from Accelerate
3 years ago
f82a7dd019
ggml : make gcc happy (minor)
3 years ago
87dd4a3081
talk.wasm : bump memory usage + update whisper.js
3 years ago
41e05c6b1b
cmake : support AVX2 in Windows better ( #381 )
3 years ago
fa379cb22a
Revert "tmp"
...
This reverts commit 1652965529
3 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
3 years ago
1652965529
tmp
3 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
3 years ago
6b351bb669
command : add "guided-mode" video demo in the README.md
3 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>
3 years ago
1944e7c33e
whisper : document POWER VSX support
3 years ago
49a8dd6732
ggml : reorganize POWER9 ppc64le SIMD code
3 years ago
8c7f642286
ggml : change f16 load and store macro arguments
3 years ago
Georgi Gerganov