Add Swift API for FireRedAsr AED Model (#1876)
This commit is contained in:
68
swift-api-examples/fire-red-asr.swift
Normal file
68
swift-api-examples/fire-red-asr.swift
Normal file
@@ -0,0 +1,68 @@
|
||||
import AVFoundation
|
||||
|
||||
extension AudioBuffer {
|
||||
func array() -> [Float] {
|
||||
return Array(UnsafeBufferPointer(self))
|
||||
}
|
||||
}
|
||||
|
||||
extension AVAudioPCMBuffer {
|
||||
func array() -> [Float] {
|
||||
return self.audioBufferList.pointee.mBuffers.array()
|
||||
}
|
||||
}
|
||||
|
||||
func run() {
|
||||
let encoder = "./sherpa-onnx-fire-red-asr-large-zh_en-2025-02-16/encoder.int8.onnx"
|
||||
let decoder = "./sherpa-onnx-fire-red-asr-large-zh_en-2025-02-16/decoder.int8.onnx"
|
||||
let tokens = "./sherpa-onnx-fire-red-asr-large-zh_en-2025-02-16/tokens.txt"
|
||||
|
||||
let fireRedAsr = sherpaOnnxOfflineFireRedAsrModelConfig(
|
||||
encoder: encoder,
|
||||
decoder: decoder
|
||||
)
|
||||
|
||||
let modelConfig = sherpaOnnxOfflineModelConfig(
|
||||
tokens: tokens,
|
||||
debug: 0,
|
||||
fireRedAsr: fireRedAsr
|
||||
)
|
||||
|
||||
let featConfig = sherpaOnnxFeatureConfig(
|
||||
sampleRate: 16000,
|
||||
featureDim: 80
|
||||
)
|
||||
var config = sherpaOnnxOfflineRecognizerConfig(
|
||||
featConfig: featConfig,
|
||||
modelConfig: modelConfig
|
||||
)
|
||||
|
||||
let recognizer = SherpaOnnxOfflineRecognizer(config: &config)
|
||||
|
||||
let filePath = "./sherpa-onnx-fire-red-asr-large-zh_en-2025-02-16/test_wavs/0.wav"
|
||||
let fileURL: NSURL = NSURL(fileURLWithPath: filePath)
|
||||
let audioFile = try! AVAudioFile(forReading: fileURL as URL)
|
||||
|
||||
let audioFormat = audioFile.processingFormat
|
||||
assert(audioFormat.channelCount == 1)
|
||||
assert(audioFormat.commonFormat == AVAudioCommonFormat.pcmFormatFloat32)
|
||||
|
||||
let audioFrameCount = UInt32(audioFile.length)
|
||||
let audioFileBuffer = AVAudioPCMBuffer(pcmFormat: audioFormat, frameCapacity: audioFrameCount)
|
||||
|
||||
try! audioFile.read(into: audioFileBuffer!)
|
||||
let array: [Float]! = audioFileBuffer?.array()
|
||||
let result = recognizer.decode(samples: array, sampleRate: Int(audioFormat.sampleRate))
|
||||
print("\nresult is:\n\(result.text)")
|
||||
if result.timestamps.count != 0 {
|
||||
print("\ntimestamps is:\n\(result.timestamps)")
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@main
|
||||
struct App {
|
||||
static func main() {
|
||||
run()
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user