Code-Inc/supertonic
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add speed parameter

Browse Source
This commit is contained in:
ANLGBOY
2025-11-19 19:42:24 +09:00
parent c31b6745e4
commit 8518b839c1
30 changed files with 246 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
go/README.md
View File

@@ -4,6 +4,8 @@ This guide provides examples for running TTS inference using `example_onnx.go`.
## 📰 Update News
**2025.11.19** - Added `--speed` parameter to control speech synthesis speed (default: 1.05, recommended range: 0.9-1.5).
**2025.11.19** - Added automatic text chunking for long-form inference. Long texts are split into chunks and synthesized with natural pauses.
## Installation

7
go/example_onnx.go
View File

@@ -15,6 +15,7 @@ type Args struct {
useGPU bool
onnxDir string
totalStep int
speed float64
nTest int
voiceStyle []string
text []string
@@ -28,6 +29,7 @@ func parseArgs() *Args {
flag.BoolVar(&args.useGPU, "use-gpu", false, "Use GPU for inference (default: CPU)")
flag.StringVar(&args.onnxDir, "onnx-dir", "assets/onnx", "Path to ONNX model directory")
flag.IntVar(&args.totalStep, "total-step", 5, "Number of denoising steps")
flag.Float64Var(&args.speed, "speed", 1.05, "Speech speed factor (higher = faster)")
flag.IntVar(&args.nTest, "n-test", 4, "Number of times to generate")
flag.StringVar(&args.saveDir, "save-dir", "results", "Output directory")
flag.BoolVar(&args.batch, "batch", false, "Enable batch mode (multiple text-style pairs)")
@@ -63,6 +65,7 @@ func main() {
// --- 1. Parse arguments --- //
args := parseArgs()
totalStep := args.totalStep
speed := float32(args.speed)
nTest := args.nTest
saveDir := args.saveDir
voiceStylePaths := args.voiceStyle
@@ -123,7 +126,7 @@ func main() {
if batch {
Timer("Generating speech from text", func() interface{} {
w, d, err := textToSpeech.Batch(textList, style, totalStep)
w, d, err := textToSpeech.Batch(textList, style, totalStep, speed)
if err != nil {
fmt.Printf("Error generating speech: %v\n", err)
os.Exit(1)
@@ -134,7 +137,7 @@ func main() {
})
} else {
Timer("Generating speech from text", func() interface{} {
w, d, err := textToSpeech.Call(textList[0], style, totalStep, 0.3)
w, d, err := textToSpeech.Call(textList[0], style, totalStep, speed, 0.3)
if err != nil {
fmt.Printf("Error generating speech: %v\n", err)
os.Exit(1)

15
go/helper.go
View File

@@ -572,7 +572,7 @@ func (tts *TextToSpeech) sampleNoisyLatent(durOnnx []float32) ([][][]float64, []
return noisyLatent, latentMask
}
func (tts *TextToSpeech) _infer(textList []string, style *Style, totalStep int) ([]float32, []float32, error) {
func (tts *TextToSpeech) _infer(textList []string, style *Style, totalStep int, speed float32) ([]float32, []float32, error) {
bsz := len(textList)
// Process text
@@ -597,6 +597,11 @@ func (tts *TextToSpeech) _infer(textList []string, style *Style, totalStep int)
durTensor := dpOutputs[0].(*ort.Tensor[float32])
defer durTensor.Destroy()
durOnnx := durTensor.GetData()
// Apply speed factor to duration
for i := range durOnnx {
durOnnx[i] /= speed
}
// Encode text
textIDsTensor2 := IntArrayToTensor(textIDs, textIDsShape)
@@ -691,14 +696,14 @@ func (tts *TextToSpeech) _infer(textList []string, style *Style, totalStep int)
}
// Call synthesizes speech from a single text with automatic chunking
func (tts *TextToSpeech) Call(text string, style *Style, totalStep int, silenceDuration float32) ([]float32, float32, error) {
func (tts *TextToSpeech) Call(text string, style *Style, totalStep int, speed float32, silenceDuration float32) ([]float32, float32, error) {
chunks := chunkText(text, 0)
var wavCat []float32
var durCat float32
for i, chunk := range chunks {
wav, duration, err := tts._infer([]string{chunk}, style, totalStep)
wav, duration, err := tts._infer([]string{chunk}, style, totalStep, speed)
if err != nil {
return nil, 0, err
}
@@ -724,8 +729,8 @@ func (tts *TextToSpeech) Call(text string, style *Style, totalStep int, silenceD
}
// Batch synthesizes speech from multiple texts
func (tts *TextToSpeech) Batch(textList []string, style *Style, totalStep int) ([]float32, []float32, error) {
return tts._infer(textList, style, totalStep)
func (tts *TextToSpeech) Batch(textList []string, style *Style, totalStep int, speed float32) ([]float32, []float32, error) {
return tts._infer(textList, style, totalStep, speed)
}
func (tts *TextToSpeech) Destroy() {