ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2024-12-18 20:27:53 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

whisper : add dtw preset for large-v3-turbo (#2481)

Browse Source
This commit is contained in:
Rotem Dan 2024-10-15 21:00:21 +03:00 committed by GitHub
parent 06a1da9daf
commit b6049060dd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
examples/main/main.cpp
View File

@ -997,6 +997,7 @@ int main(int argc, char ** argv) {
if (params.dtw == "large.v1") cparams.dtw_aheads_preset = WHISPER_AHEADS_LARGE_V1; if (params.dtw == "large.v1") cparams.dtw_aheads_preset = WHISPER_AHEADS_LARGE_V1;
if (params.dtw == "large.v2") cparams.dtw_aheads_preset = WHISPER_AHEADS_LARGE_V2; if (params.dtw == "large.v2") cparams.dtw_aheads_preset = WHISPER_AHEADS_LARGE_V2;
if (params.dtw == "large.v3") cparams.dtw_aheads_preset = WHISPER_AHEADS_LARGE_V3; if (params.dtw == "large.v3") cparams.dtw_aheads_preset = WHISPER_AHEADS_LARGE_V3;
if (params.dtw == "large.v3.turbo") cparams.dtw_aheads_preset = WHISPER_AHEADS_LARGE_V3_TURBO;
if (cparams.dtw_aheads_preset == WHISPER_AHEADS_NONE) { if (cparams.dtw_aheads_preset == WHISPER_AHEADS_NONE) {
fprintf(stderr, "error: unknown DTW preset '%s'\n", params.dtw.c_str()); fprintf(stderr, "error: unknown DTW preset '%s'\n", params.dtw.c_str());

1
include/whisper.h
View File

@ -99,6 +99,7 @@ extern "C" {
WHISPER_AHEADS_LARGE_V1, WHISPER_AHEADS_LARGE_V1,
WHISPER_AHEADS_LARGE_V2, WHISPER_AHEADS_LARGE_V2,
WHISPER_AHEADS_LARGE_V3, WHISPER_AHEADS_LARGE_V3,
WHISPER_AHEADS_LARGE_V3_TURBO,
}; };
typedef struct whisper_ahead { typedef struct whisper_ahead {

2
src/whisper.cpp
View File

@ -381,6 +381,7 @@ static const whisper_ahead g_aheads_medium[] = { {13, 15}, {15, 4}, {15, 15},
static const whisper_ahead g_aheads_large_v1[] = { {9, 19}, {11, 2}, {11, 4}, {11, 17}, {22, 7}, {22, 11}, {22, 17}, {23, 2}, {23, 15} }; static const whisper_ahead g_aheads_large_v1[] = { {9, 19}, {11, 2}, {11, 4}, {11, 17}, {22, 7}, {22, 11}, {22, 17}, {23, 2}, {23, 15} };
static const whisper_ahead g_aheads_large_v2[] = { {10, 12}, {13, 17}, {16, 11}, {16, 12}, {16, 13}, {17, 15}, {17, 16}, {18, 4}, {18, 11}, {18, 19}, {19, 11}, {21, 2}, {21, 3}, {22, 3}, {22, 9}, {22, 12}, {23, 5}, {23, 7}, {23, 13}, {25, 5}, {26, 1}, {26, 12}, {27, 15} }; static const whisper_ahead g_aheads_large_v2[] = { {10, 12}, {13, 17}, {16, 11}, {16, 12}, {16, 13}, {17, 15}, {17, 16}, {18, 4}, {18, 11}, {18, 19}, {19, 11}, {21, 2}, {21, 3}, {22, 3}, {22, 9}, {22, 12}, {23, 5}, {23, 7}, {23, 13}, {25, 5}, {26, 1}, {26, 12}, {27, 15} };
static const whisper_ahead g_aheads_large_v3[] = { {7, 0}, {10, 17}, {12, 18}, {13, 12}, {16, 1}, {17, 14}, {19, 11}, {21, 4}, {24, 1}, {25, 6} }; static const whisper_ahead g_aheads_large_v3[] = { {7, 0}, {10, 17}, {12, 18}, {13, 12}, {16, 1}, {17, 14}, {19, 11}, {21, 4}, {24, 1}, {25, 6} };
static const whisper_ahead g_aheads_large_v3_turbo[] = { {2, 4}, {2, 11}, {3, 3}, {3, 6}, {3, 11}, {3, 14} };
static const std::map<whisper_alignment_heads_preset, whisper_aheads> g_aheads { static const std::map<whisper_alignment_heads_preset, whisper_aheads> g_aheads {
{ WHISPER_AHEADS_TINY_EN, { 8, g_aheads_tiny_en } }, { WHISPER_AHEADS_TINY_EN, { 8, g_aheads_tiny_en } },
@ -394,6 +395,7 @@ static const std::map<whisper_alignment_heads_preset, whisper_aheads> g_aheads {
{ WHISPER_AHEADS_LARGE_V1, { 9, g_aheads_large_v1 } }, { WHISPER_AHEADS_LARGE_V1, { 9, g_aheads_large_v1 } },
{ WHISPER_AHEADS_LARGE_V2, { 23, g_aheads_large_v2 } }, { WHISPER_AHEADS_LARGE_V2, { 23, g_aheads_large_v2 } },
{ WHISPER_AHEADS_LARGE_V3, { 10, g_aheads_large_v3 } }, { WHISPER_AHEADS_LARGE_V3, { 10, g_aheads_large_v3 } },
{ WHISPER_AHEADS_LARGE_V3_TURBO, { 6, g_aheads_large_v3_turbo } },
}; };
static std::vector<uint32_t> get_alignment_heads_by_layer(const whisper_context_params & cparams, int il, int32_t n_text_layer, int32_t n_head); static std::vector<uint32_t> get_alignment_heads_by_layer(const whisper_context_params & cparams, int il, int32_t n_text_layer, int32_t n_head);