LocalAI/core/backend/transcript.go
Dave c4f958e11b
refactor(application): introduce application global state (#2072)
* start breaking up the giant channel refactor now that it's better understood - easier to merge bites

Signed-off-by: Dave Lee <dave@gray101.com>

* add concurrency and base64 back in, along with new base64 tests.

Signed-off-by: Dave Lee <dave@gray101.com>

* Automatic rename of whisper.go's Result to TranscriptResult

Signed-off-by: Dave Lee <dave@gray101.com>

* remove pkg/concurrency - significant changes coming in split 2

Signed-off-by: Dave Lee <dave@gray101.com>

* fix comments

Signed-off-by: Dave Lee <dave@gray101.com>

* add list_model service as another low-risk service to get it out of the way

Signed-off-by: Dave Lee <dave@gray101.com>

* split backend config loader into seperate file from the actual config struct. No changes yet, just reduce cognative load with smaller files of logical blocks

Signed-off-by: Dave Lee <dave@gray101.com>

* rename state.go ==> application.go

Signed-off-by: Dave Lee <dave@gray101.com>

* fix lost import?

Signed-off-by: Dave Lee <dave@gray101.com>

---------

Signed-off-by: Dave Lee <dave@gray101.com>
2024-04-29 17:42:37 +00:00

39 lines
1.0 KiB
Go

package backend
import (
"context"
"fmt"
"github.com/go-skynet/LocalAI/core/config"
"github.com/go-skynet/LocalAI/core/schema"
"github.com/go-skynet/LocalAI/pkg/grpc/proto"
model "github.com/go-skynet/LocalAI/pkg/model"
)
func ModelTranscription(audio, language string, ml *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (*schema.TranscriptionResult, error) {
opts := modelOpts(backendConfig, appConfig, []model.Option{
model.WithBackendString(model.WhisperBackend),
model.WithModel(backendConfig.Model),
model.WithContext(appConfig.Context),
model.WithThreads(uint32(*backendConfig.Threads)),
model.WithAssetDir(appConfig.AssetsDestination),
})
whisperModel, err := ml.BackendLoader(opts...)
if err != nil {
return nil, err
}
if whisperModel == nil {
return nil, fmt.Errorf("could not load whisper model")
}
return whisperModel.AudioTranscription(context.Background(), &proto.TranscriptRequest{
Dst: audio,
Language: language,
Threads: uint32(*backendConfig.Threads),
})
}