LocalAI/core/cli/soundgeneration.go
Ettore Di Giacinto 2c425e9c69
Some checks are pending
Explorer deployment / build-linux (push) Waiting to run
GPU tests / ubuntu-latest (1.21.x) (push) Waiting to run
generate and publish intel docker caches / generate_caches (intel/oneapi-basekit:2025.0.0-0-devel-ubuntu22.04, linux/amd64, ubuntu-latest) (push) Waiting to run
build container images / hipblas-jobs (-aio-gpu-hipblas, rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, extras, latest-gpu-hipblas, latest-aio-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -hipblas-ffmpeg) (push) Waiting to run
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, false, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas-core) (push) Waiting to run
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, false, ubuntu:22.04, extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas) (push) Waiting to run
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas-ffmpeg-core) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-intel-f16, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, extras, latest-gpu-intel-f16, latest-aio-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -sycl-f16-ffmpeg) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-intel-f32, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, extras, latest-gpu-intel-f32, latest-aio-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -sycl-f32-ffmpeg) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-11, ubuntu:22.04, cublas, 11, 7, true, extras, latest-gpu-nvidia-cuda-11, latest-aio-gpu-nvidia-cuda-11, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -cublas-cuda11-ffmpeg) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-12, ubuntu:22.04, cublas, 12, 0, true, extras, latest-gpu-nvidia-cuda-12, latest-aio-gpu-nvidia-cuda-12, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -cublas-cuda12-ffmpeg) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, false, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16-core) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16-ffmpeg-core) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, false, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32-core) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32-ffmpeg-core) (push) Waiting to run
build container images / self-hosted-jobs (ubuntu:22.04, , , extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, ) (push) Waiting to run
build container images / self-hosted-jobs (ubuntu:22.04, , true, extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -ffmpeg) (push) Waiting to run
build container images / self-hosted-jobs (ubuntu:22.04, cublas, 11, 7, , extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda11) (push) Waiting to run
build container images / self-hosted-jobs (ubuntu:22.04, cublas, 12, 0, , extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda12) (push) Waiting to run
build container images / core-image-build (-aio-cpu, ubuntu:22.04, , true, core, latest-cpu, latest-aio-cpu, --jobs=4 --output-sync=target, linux/amd64,linux/arm64, arc-runner-set, false, auto, -ffmpeg-core) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 11, 7, , core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda11-core) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 11, 7, true, core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda11-ffmpeg-core) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 12, 0, , core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda12-core) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 12, 0, true, core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda12-ffmpeg-core) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, vulkan, true, core, latest-vulkan-ffmpeg-core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -vulkan-ffmpeg-core) (push) Waiting to run
build container images / gh-runner (nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, 12, 0, true, core, latest-nvidia-l4t-arm64-core, --jobs=4 --output-sync=target, linux/arm64, ubuntu-24.04-arm, true, false, -nvidia-l4t-arm64-core) (push) Waiting to run
Security Scan / tests (push) Waiting to run
Tests extras backends / tests-transformers (push) Waiting to run
Tests extras backends / tests-rerankers (push) Waiting to run
Tests extras backends / tests-diffusers (push) Waiting to run
Tests extras backends / tests-coqui (push) Waiting to run
tests / tests-linux (1.21.x) (push) Waiting to run
tests / tests-aio-container (push) Waiting to run
tests / tests-apple (1.21.x) (push) Waiting to run
feat(loader): enhance single active backend by treating as singleton (#5107)
feat(loader): enhance single active backend by treating at singleton

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-04-01 20:58:11 +02:00

113 lines
3.7 KiB
Go

package cli
import (
"context"
"fmt"
"os"
"path/filepath"
"strconv"
"strings"
"github.com/mudler/LocalAI/core/backend"
cliContext "github.com/mudler/LocalAI/core/cli/context"
"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/pkg/model"
"github.com/rs/zerolog/log"
)
type SoundGenerationCMD struct {
Text []string `arg:""`
Backend string `short:"b" required:"" help:"Backend to run the SoundGeneration model"`
Model string `short:"m" required:"" help:"Model name to run the SoundGeneration"`
Duration string `short:"d" help:"If specified, the length of audio to generate in seconds"`
Temperature string `short:"t" help:"If specified, the temperature of the generation"`
InputFile string `short:"i" help:"If specified, the input file to condition generation upon"`
InputFileSampleDivisor string `short:"f" help:"If InputFile and this divisor is specified, the first portion of the sample file will be used"`
DoSample bool `short:"s" default:"true" help:"Enables sampling from the model. Better quality at the cost of speed. Defaults to enabled."`
OutputFile string `short:"o" type:"path" help:"The path to write the output wav file"`
ModelsPath string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
BackendAssetsPath string `env:"LOCALAI_BACKEND_ASSETS_PATH,BACKEND_ASSETS_PATH" type:"path" default:"/tmp/localai/backend_data" help:"Path used to extract libraries that are required by some of the backends in runtime" group:"storage"`
ExternalGRPCBackends []string `env:"LOCALAI_EXTERNAL_GRPC_BACKENDS,EXTERNAL_GRPC_BACKENDS" help:"A list of external grpc backends" group:"backends"`
}
func parseToFloat32Ptr(input string) *float32 {
f, err := strconv.ParseFloat(input, 32)
if err != nil {
return nil
}
f2 := float32(f)
return &f2
}
func parseToInt32Ptr(input string) *int32 {
i, err := strconv.ParseInt(input, 10, 32)
if err != nil {
return nil
}
i2 := int32(i)
return &i2
}
func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
outputFile := t.OutputFile
outputDir := t.BackendAssetsPath
if outputFile != "" {
outputDir = filepath.Dir(outputFile)
}
text := strings.Join(t.Text, " ")
externalBackends := make(map[string]string)
// split ":" to get backend name and the uri
for _, v := range t.ExternalGRPCBackends {
backend := v[:strings.IndexByte(v, ':')]
uri := v[strings.IndexByte(v, ':')+1:]
externalBackends[backend] = uri
fmt.Printf("TMP externalBackends[%q]=%q\n\n", backend, uri)
}
opts := &config.ApplicationConfig{
ModelPath: t.ModelsPath,
Context: context.Background(),
AudioDir: outputDir,
AssetsDestination: t.BackendAssetsPath,
ExternalGRPCBackends: externalBackends,
}
ml := model.NewModelLoader(opts.ModelPath, opts.SingleBackend)
defer func() {
err := ml.StopAllGRPC()
if err != nil {
log.Error().Err(err).Msg("unable to stop all grpc processes")
}
}()
options := config.BackendConfig{}
options.SetDefaults()
options.Backend = t.Backend
options.Model = t.Model
var inputFile *string
if t.InputFile != "" {
inputFile = &t.InputFile
}
filePath, _, err := backend.SoundGeneration(text,
parseToFloat32Ptr(t.Duration), parseToFloat32Ptr(t.Temperature), &t.DoSample,
inputFile, parseToInt32Ptr(t.InputFileSampleDivisor), ml, opts, options)
if err != nil {
return err
}
if outputFile != "" {
if err := os.Rename(filePath, outputFile); err != nil {
return err
}
fmt.Printf("Generate file %s\n", outputFile)
} else {
fmt.Printf("Generate file %s\n", filePath)
}
return nil
}