13204489d7
Merge 5567eaaa1c into 1a91c19af9
3 years ago
1a91c19af9
whisper : perform entropy check only when we have at least 32 tokens ( #412 )
3 years ago
f583e2d2f5
main : we had accidentally disabled the temperature fallback .. ( #291 )
3 years ago
206fc93396
whisper.wasm : add small and small.en models
3 years ago
a6cf6f4c4a
bench : minor fixes
3 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>
3 years ago
9ba66c2fad
stream : fix handling of --step == --length ( #416 )
3 years ago
1ccb8a46a5
bench : fix Windows linkage by moving ggml benches in whisper lib ..
3 years ago
1290fc6457
bench : add memcpy and ggml_mul_mat benchmarks
3 years ago
49b529ba74
whisper.android : add support for loading directly from asset in C ( #415 )
3 years ago
8088a977af
whisper : fix possible uninitialized variables ( #291 )
3 years ago
c9aeb33676
stream : fix --keep_context argument to be used correctly ( #354 )
3 years ago
4a3f0d3fe9
go : remove sample_best and sample_timestamp bindings ( #409 )
3 years ago
874bde887e
Update README.md
3 years ago
5567eaaa1c
Use GetProcessTimes for process time on Windows
3 years ago
8738427dd6
cmake : bump version to 1.1.0
3 years ago
c3991bbb24
Update README.md
3 years ago
896197c194
Update gpt-2.cpp
3 years ago
00ea21668b
whisper : account speed_up flag for short audio ( close #405 )
3 years ago
07ff91c3fe
bench-all : shorten the Thread column
3 years ago
d573de4f94
Cosmetic stuff
3 years ago
e22836e394
Add back GGML_PERF flag
3 years ago
b3c76307a9
Add windows process-specific timings
3 years ago
f725df5528
Improve configuration detection in bench-all
3 years ago
de6e97a9ed
Add result message to and format output of bench-all
3 years ago
e858f410da
Add process time to bench-all script
3 years ago
3abcfc6fc3
Add process time to whisper_print_timings
3 years ago
bde7ee3751
Remove ggml_cycles and ggml_perf timings; replace with ggml_process_time
3 years ago
0b85e8c401
Update README.md
3 years ago
fafd78945d
bench.wasm : print system info
3 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
3 years ago
a6dbd9188b
stream : fix a bug that inserted a lot of empty audio at the start
...
The quality was terrible due to this
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
Abitofevrything