ae16c21e9c
whisper : PPC64 big-endian support ( #398 )
...
* ggml : set cache line size to 128 on POWER9
* whisper : add PPC64 big endian support
1 year ago
2c3f50a021
release : v1.1.1
1 year ago
9a65269a20
.gitignore : add arm_neon.h
1 year ago
78f166174f
whisper : fix condition for providing past prompt (critical)
...
This bug has been present since v1.1.0.
Effectively, the past transcribed text wasn't being used for following
transcriptions, which likely significantly reduces the transcription
quality.
Likely related to #419
1 year ago
21c569ba4a
whisper : extend information in whisper_print_timings()
1 year ago
1a91c19af9
whisper : perform entropy check only when we have at least 32 tokens ( #412 )
1 year ago
f583e2d2f5
main : we had accidentally disabled the temperature fallback .. ( #291 )
1 year ago
206fc93396
whisper.wasm : add small and small.en models
1 year ago
a6cf6f4c4a
bench : minor fixes
1 year 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>
1 year ago
9ba66c2fad
stream : fix handling of --step == --length ( #416 )
1 year ago
1ccb8a46a5
bench : fix Windows linkage by moving ggml benches in whisper lib ..
1 year ago
1290fc6457
bench : add memcpy and ggml_mul_mat benchmarks
1 year ago
49b529ba74
whisper.android : add support for loading directly from asset in C ( #415 )
1 year ago
8088a977af
whisper : fix possible uninitialized variables ( #291 )
1 year ago
c9aeb33676
stream : fix --keep_context argument to be used correctly ( #354 )
1 year ago
4a3f0d3fe9
go : remove sample_best and sample_timestamp bindings ( #409 )
1 year ago
874bde887e
Update README.md
1 year ago
8738427dd6
cmake : bump version to 1.1.0
1 year ago
c3991bbb24
Update README.md
1 year ago
00ea21668b
whisper : account speed_up flag for short audio ( close #405 )
1 year ago
0b85e8c401
Update README.md
1 year ago
fafd78945d
bench.wasm : print system info
1 year 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
1 year ago
a6dbd9188b
stream : fix a bug that inserted a lot of empty audio at the start
...
The quality was terrible due to this
1 year ago
4ef3398e8f
ggml : remove obsolete zeroing + comment fixes ( #390 )
1 year 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`
1 year ago
8d7b29cedd
ggml : correct behaviour of ggml_vec_sum_f32 ( #390 )
1 year 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>
1 year 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>
1 year ago
52a3e0c92a
ggml : improve vec_dot_f16 unrolling in flash_attn_f16
1 year ago
d1ea1220ff
command : clean-up / refactoring / formatting ( #383 )
1 year ago
9c4a1522f6
command : always-prompt mode ( #383 )
1 year 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
1 year ago
f30b5d322c
ggml : fix bug in new soft max computation
1 year ago
44efbf7ff1
cmake : add -Wno-unused-function + update whisper.js
1 year ago
d347a59a5f
ggml : when using BLAS start only 1 CPU thread
1 year ago
6394c906af
ggml : fix running tasks with variable number of threads
1 year ago
74ffa14e1d
ggml : unroll ggml_vec_dot_f16 in ggml_compute_forward_flash_attn_f16
1 year ago
65fdcbbbbb
whisper : revert accidental MB change
1 year ago
d61d55cd4b
ggml : speed-up soft max via Accelerate + unroll
1 year ago
d51fc3ee0a
ggml : use vDSP_sve and vDSP_maxv from Accelerate
1 year ago
f82a7dd019
ggml : make gcc happy (minor)
1 year ago
87dd4a3081
talk.wasm : bump memory usage + update whisper.js
1 year ago
41e05c6b1b
cmake : support AVX2 in Windows better ( #381 )
1 year ago
fa379cb22a
Revert "tmp"
...
This reverts commit 1652965529
1 year 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
1 year ago
1652965529
tmp
1 year 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
1 year ago
6b351bb669
command : add "guided-mode" video demo in the README.md
1 year ago
fitzsim
Georgi Gerganov
Chia-Hsiang Cheng
Digipom
Damian Czaja
Ian Bicking
Abitofevrything
boolemancer
Syahmi Azhar
David
David Thorpe
m.bell