2c3f50a021
release : v1.1.1
2023-01-23 20:23:44 +02:00
9a65269a20
.gitignore : add arm_neon.h
2023-01-23 20:19:04 +02:00
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
2023-01-22 10:47:01 +02:00
21c569ba4a
whisper : extend information in whisper_print_timings()
2023-01-19 18:50:33 +02:00
1a91c19af9
whisper : perform entropy check only when we have at least 32 tokens ( #412 )
2023-01-18 22:52:18 +02:00
f583e2d2f5
main : we had accidentally disabled the temperature fallback .. ( #291 )
2023-01-18 22:51:41 +02:00
206fc93396
whisper.wasm : add small and small.en models
2023-01-18 21:58:55 +02:00
a6cf6f4c4a
bench : minor fixes
2023-01-18 21:40:10 +02:00
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 >
2023-01-18 21:26:31 +02:00
9ba66c2fad
stream : fix handling of --step == --length ( #416 )
2023-01-18 21:22:52 +02:00
1ccb8a46a5
bench : fix Windows linkage by moving ggml benches in whisper lib ..
2023-01-18 21:19:50 +02:00
1290fc6457
bench : add memcpy and ggml_mul_mat benchmarks
2023-01-18 20:31:46 +02:00
49b529ba74
whisper.android : add support for loading directly from asset in C ( #415 )
2023-01-16 21:57:35 +02:00
8088a977af
whisper : fix possible uninitialized variables ( #291 )
2023-01-16 21:44:40 +02:00
c9aeb33676
stream : fix --keep_context argument to be used correctly ( #354 )
2023-01-16 19:37:40 +02:00
4a3f0d3fe9
go : remove sample_best and sample_timestamp bindings ( #409 )
2023-01-16 19:18:10 +02:00
874bde887e
Update README.md
2023-01-16 18:47:31 +02:00
8738427dd6
cmake : bump version to 1.1.0
2023-01-15 14:33:13 +02:00
c3991bbb24
Update README.md
2023-01-15 14:08:12 +02:00
00ea21668b
whisper : account speed_up flag for short audio ( close #405 )
2023-01-15 12:42:15 +02:00
0b85e8c401
Update README.md
2023-01-15 11:36:20 +02:00
fafd78945d
bench.wasm : print system info
2023-01-15 11:34:03 +02:00
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
2023-01-15 11:29:57 +02:00
a6dbd9188b
stream : fix a bug that inserted a lot of empty audio at the start
...
The quality was terrible due to this
2023-01-14 19:20:47 +02:00
4ef3398e8f
ggml : remove obsolete zeroing + comment fixes ( #390 )
2023-01-08 20:21:03 +02:00
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`
2023-01-08 20:18:41 +02:00
8d7b29cedd
ggml : correct behaviour of ggml_vec_sum_f32 ( #390 )
2023-01-08 20:06:09 +02:00
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 >
2023-01-08 15:08:45 +02:00
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 >
2023-01-08 13:03:33 +02:00
52a3e0c92a
ggml : improve vec_dot_f16 unrolling in flash_attn_f16
2023-01-08 11:41:18 +02:00
d1ea1220ff
command : clean-up / refactoring / formatting ( #383 )
2023-01-07 21:43:24 +02:00
9c4a1522f6
command : always-prompt mode ( #383 )
2023-01-07 21:41:11 +02:00
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
2023-01-07 21:21:43 +02:00
f30b5d322c
ggml : fix bug in new soft max computation
2023-01-07 21:00:07 +02:00
44efbf7ff1
cmake : add -Wno-unused-function + update whisper.js
2023-01-07 20:18:34 +02:00
d347a59a5f
ggml : when using BLAS start only 1 CPU thread
2023-01-07 19:48:56 +02:00
6394c906af
ggml : fix running tasks with variable number of threads
2023-01-07 19:20:18 +02:00
74ffa14e1d
ggml : unroll ggml_vec_dot_f16 in ggml_compute_forward_flash_attn_f16
2023-01-07 19:19:40 +02:00
65fdcbbbbb
whisper : revert accidental MB change
2023-01-07 16:18:21 +02:00
d61d55cd4b
ggml : speed-up soft max via Accelerate + unroll
2023-01-07 16:16:42 +02:00
d51fc3ee0a
ggml : use vDSP_sve and vDSP_maxv from Accelerate
2023-01-07 16:10:16 +02:00
f82a7dd019
ggml : make gcc happy (minor)
2023-01-07 09:34:39 +02:00
87dd4a3081
talk.wasm : bump memory usage + update whisper.js
2023-01-06 21:13:44 +02:00
41e05c6b1b
cmake : support AVX2 in Windows better ( #381 )
2023-01-06 19:36:33 +02:00
fa379cb22a
Revert "tmp"
...
This reverts commit 1652965529
2023-01-06 19:33:09 +02:00
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
2023-01-06 19:32:28 +02:00
1652965529
tmp
2023-01-06 19:32:12 +02:00
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
2023-01-06 19:25:28 +02:00
6b351bb669
command : add "guided-mode" video demo in the README.md
2023-01-06 18:59:26 +02:00
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 >
2023-01-06 18:45:59 +02:00
