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

go : add SetInitialPrompt method to bindings (#1753)

Browse Source
This commit is contained in:
Boris Bliznioukov 2024-01-12 14:44:50 +03:00 committed by GitHub
parent fbcb52d3cd
commit 5cb345f5e9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 23 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
bindings/go/params.go
View File

@ -123,6 +123,11 @@ func (p *Params) SetAudioCtx(n int) {
p.audio_ctx = C.int(n)
}
// Set initial prompt
func (p *Params) SetInitialPrompt(prompt string) {
p.initial_prompt = C.CString(prompt)
}
///////////////////////////////////////////////////////////////////////////////
// PRIVATE METHODS
@ -147,6 +152,7 @@ func (p *Params) String() string {
str += fmt.Sprintf(" offset_ms=%d", p.offset_ms)
str += fmt.Sprintf(" duration_ms=%d", p.duration_ms)
str += fmt.Sprintf(" audio_ctx=%d", p.audio_ctx)
str += fmt.Sprintf(" initial_prompt=%s", C.GoString(p.initial_prompt))
if p.translate {
str += " translate"
}

5
bindings/go/pkg/whisper/context.go
View File

@ -130,6 +130,11 @@ func (context *context) SetAudioCtx(n uint) {
context.params.SetAudioCtx(int(n))
}
// Set initial prompt
func (context *context) SetInitialPrompt(prompt string) {
context.params.SetInitialPrompt(prompt)
}
// ResetTimings resets the mode timings. Should be called before processing
func (context *context) ResetTimings() {
context.model.ctx.Whisper_reset_timings()

23
bindings/go/pkg/whisper/interface.go
View File

@ -38,17 +38,18 @@ type Context interface {
IsMultilingual() bool // Return true if the model is multilingual.
Language() string // Get language
SetOffset(time.Duration) // Set offset
SetDuration(time.Duration) // Set duration
SetThreads(uint) // Set number of threads to use
SetSpeedup(bool) // Set speedup flag
SetSplitOnWord(bool) // Set split on word flag
SetTokenThreshold(float32) // Set timestamp token probability threshold
SetTokenSumThreshold(float32) // Set timestamp token sum probability threshold
SetMaxSegmentLength(uint) // Set max segment length in characters
SetTokenTimestamps(bool) // Set token timestamps flag
SetMaxTokensPerSegment(uint) // Set max tokens per segment (0 = no limit)
SetAudioCtx(uint) // Set audio encoder context
SetOffset(time.Duration) // Set offset
SetDuration(time.Duration) // Set duration
SetThreads(uint) // Set number of threads to use
SetSpeedup(bool) // Set speedup flag
SetSplitOnWord(bool) // Set split on word flag
SetTokenThreshold(float32) // Set timestamp token probability threshold
SetTokenSumThreshold(float32) // Set timestamp token sum probability threshold
SetMaxSegmentLength(uint) // Set max segment length in characters
SetTokenTimestamps(bool) // Set token timestamps flag
SetMaxTokensPerSegment(uint) // Set max tokens per segment (0 = no limit)
SetAudioCtx(uint) // Set audio encoder context
SetInitialPrompt(prompt string) // Set initial prompt
// Process mono audio data and return any errors.
// If defined, newly generated segments are passed to the