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

10
swift/Sources/ExampleONNX.swift
View File

@@ -5,6 +5,7 @@ struct Args {
var useGpu: Bool = false
var onnxDir: String = "assets/onnx"
var totalStep: Int = 5
var speed: Float = 1.05
var nTest: Int = 4
var voiceStyle: [String] = ["assets/voice_styles/M1.json"]
var text: [String] = ["This morning, I took a walk in the park, and the sound of the birds and the breeze was so pleasant that I stopped for a long time just to listen."]
@@ -33,6 +34,11 @@ func parseArgs() -> Args {
args.totalStep = Int(arguments[i + 1]) ?? 5
i += 1
}
case "--speed":
if i + 1 < arguments.count {
args.speed = Float(arguments[i + 1]) ?? 1.05
i += 1
}
case "--n-test":
if i + 1 < arguments.count {
args.nTest = Int(arguments[i + 1]) ?? 4
@@ -102,13 +108,13 @@ struct ExampleONNX {
if args.batch {
let result = try timer("Generating speech from text") {
try textToSpeech.batch(args.text, style, args.totalStep)
try textToSpeech.batch(args.text, style, args.totalStep, speed: args.speed)
}
wav = result.wav
duration = result.duration
} else {
let result = try timer("Generating speech from text") {
try textToSpeech.call(args.text[0], style, args.totalStep, silenceDuration: 0.3)
try textToSpeech.call(args.text[0], style, args.totalStep, speed: args.speed, silenceDuration: 0.3)
}
wav = result.wav
duration = [result.duration]

17
swift/Sources/Helper.swift
View File

@@ -453,7 +453,7 @@ class TextToSpeech {
self.sampleRate = cfgs.ae.sample_rate
}
private func _infer(_ textList: [String], _ style: Style, _ totalStep: Int) throws -> (wav: [Float], duration: [Float]) {
private func _infer(_ textList: [String], _ style: Style, _ totalStep: Int, speed: Float = 1.05) throws -> (wav: [Float], duration: [Float]) {
let bsz = textList.count
// Process text
@@ -479,10 +479,15 @@ class TextToSpeech {
runOptions: nil)
let durationData = try dpOutputs["duration"]!.tensorData() as Data
let duration = durationData.withUnsafeBytes { ptr in
var duration = durationData.withUnsafeBytes { ptr in
Array(ptr.bindMemory(to: Float.self))
}
// Apply speed factor to duration
for i in 0..<duration.count {
duration[i] /= speed
}
// Encode text
let textEncOutputs = try textEncOrt.run(withInputs: ["text_ids": textIdsValue, "style_ttl": style.ttl, "text_mask": textMaskValue],
outputNames: ["text_emb"],
@@ -576,14 +581,14 @@ class TextToSpeech {
return (wav, duration)
}
func call(_ text: String, _ style: Style, _ totalStep: Int, silenceDuration: Float) throws -> (wav: [Float], duration: Float) {
func call(_ text: String, _ style: Style, _ totalStep: Int, speed: Float = 1.05, silenceDuration: Float = 0.3) throws -> (wav: [Float], duration: Float) {
let chunks = chunkText(text)
var wavCat = [Float]()
var durCat: Float = 0.0
for (i, chunk) in chunks.enumerated() {
let result = try _infer([chunk], style, totalStep)
let result = try _infer([chunk], style, totalStep, speed: speed)
let dur = result.duration[0]
let wavLen = Int(Float(sampleRate) * dur)
@@ -605,8 +610,8 @@ class TextToSpeech {
return (wavCat, durCat)
}
func batch(_ textList: [String], _ style: Style, _ totalStep: Int) throws -> (wav: [Float], duration: [Float]) {
return try _infer(textList, style, totalStep)
func batch(_ textList: [String], _ style: Style, _ totalStep: Int, speed: Float = 1.05) throws -> (wav: [Float], duration: [Float]) {
return try _infer(textList, style, totalStep, speed: speed)
}
}