LocalAI/pkg/utils/ffmpeg.go
Richard Palethorpe bf6426aef2
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:2025.1.0-0-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-extras, latest-aio-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -hipblas-extras) (push) Waiting to run
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, core, latest-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas) (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-extras, latest-aio-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16-… (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-extras, latest-aio-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32-… (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-extras, latest-aio-gpu-nvidia-cuda-11, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda11-extras) (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-extras, latest-aio-gpu-nvidia-cuda-12, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda12-extras) (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, latest-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16) (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, latest-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32) (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, ) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 11, 7, true, core, latest-gpu-nvidia-cuda-12, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda11) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 12, 0, true, core, latest-gpu-nvidia-cuda-12, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda12) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, vulkan, true, core, latest-gpu-vulkan, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -vulkan) (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, --jobs=4 --output-sync=target, linux/arm64, ubuntu-24.04-arm, true, false, -nvidia-l4t-arm64) (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: Realtime API support reboot (#5392)
* feat(realtime): Initial Realtime API implementation

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore: go mod tidy

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* feat: Implement transcription only mode for realtime API

Reduce the scope of the real time API for the initial realease and make
transcription only mode functional.

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* chore(build): Build backends on a separate layer to speed up core only changes

Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Richard Palethorpe <io@richiejp.com>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2025-05-25 22:25:05 +02:00

72 lines
1.8 KiB
Go

package utils
import (
"fmt"
"os"
"os/exec"
"strings"
"github.com/go-audio/wav"
)
func ffmpegCommand(args []string) (string, error) {
cmd := exec.Command("ffmpeg", args...) // Constrain this to ffmpeg to permit security scanner to see that the command is safe.
cmd.Env = os.Environ()
out, err := cmd.CombinedOutput()
return string(out), err
}
// AudioToWav converts audio to wav for transcribe.
// TODO: use https://github.com/mccoyst/ogg?
func AudioToWav(src, dst string) error {
if strings.HasSuffix(src, ".wav") {
f, err := os.Open(src)
if err != nil {
return fmt.Errorf("open: %w", err)
}
dec := wav.NewDecoder(f)
dec.ReadInfo()
f.Close()
if dec.BitDepth == 16 && dec.NumChans == 1 && dec.SampleRate == 16000 {
os.Rename(src, dst)
return nil
}
}
commandArgs := []string{"-i", src, "-format", "s16le", "-ar", "16000", "-ac", "1", "-acodec", "pcm_s16le", dst}
out, err := ffmpegCommand(commandArgs)
if err != nil {
return fmt.Errorf("error: %w out: %s", err, out)
}
return nil
}
// AudioConvert converts generated wav file from tts to other output formats.
// TODO: handle pcm to have 100% parity of supported format from OpenAI
func AudioConvert(src string, format string) (string, error) {
extension := ""
// compute file extension from format, default to wav
switch format {
case "opus":
extension = ".ogg"
case "mp3", "aac", "flac":
extension = fmt.Sprintf(".%s", format)
default:
extension = ".wav"
}
// if .wav, do nothing
if extension == ".wav" {
return src, nil
}
// naive conversion based on default values and target extension of file
dst := strings.Replace(src, ".wav", extension, -1)
commandArgs := []string{"-y", "-i", src, "-vn", dst}
out, err := ffmpegCommand(commandArgs)
if err != nil {
return "", fmt.Errorf("error: %w out: %s", err, out)
}
return dst, nil
}