supertonic 3

This commit is contained in:
haeon
2026-05-06 23:09:06 +02:00
parent 6fc89ea89e
commit 0a98c9f127
47 changed files with 530 additions and 411 deletions

View File

@@ -3,11 +3,11 @@ import OnnxRuntimeBindings
struct Args {
var useGpu: Bool = false
var onnxDir: String = "assets/onnx"
var totalStep: Int = 5
var onnxDir: String = "../assets/onnx"
var totalStep: Int = 8
var speed: Float = 1.05
var nTest: Int = 4
var voiceStyle: [String] = ["assets/voice_styles/M1.json"]
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."]
var lang: [String] = ["en"]
var saveDir: String = "results"
@@ -32,7 +32,7 @@ func parseArgs() -> Args {
}
case "--total-step":
if i + 1 < arguments.count {
args.totalStep = Int(arguments[i + 1]) ?? 5
args.totalStep = Int(arguments[i + 1]) ?? 8
i += 1
}
case "--speed":

View File

@@ -4,7 +4,7 @@ import OnnxRuntimeBindings
// MARK: - Available Languages
let AVAILABLE_LANGS = ["en", "ko", "es", "pt", "fr"]
let AVAILABLE_LANGS = ["en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi"]
func isValidLang(_ lang: String) -> Bool {
return AVAILABLE_LANGS.contains(lang)
@@ -701,7 +701,7 @@ class TextToSpeech {
}
func call(_ text: String, _ lang: String, _ style: Style, _ totalStep: Int, speed: Float = 1.05, silenceDuration: Float = 0.3) throws -> (wav: [Float], duration: Float) {
let maxLen = lang == "ko" ? 120 : 300
let maxLen = (lang == "ko" || lang == "ja") ? 120 : 300
let chunks = chunkText(text, maxLen: maxLen)
let langList = Array(repeating: lang, count: chunks.count)