EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Support streaming zipformer CTC (#496)

Browse Source 
* Support streaming zipformer CTC

* test online zipformer2 CTC

* Update doc of sherpa-onnx.cc

* Add Python APIs for streaming zipformer2 ctc

* Add Python API examples for streaming zipformer2 ctc

* Swift API for streaming zipformer2 CTC

* NodeJS API for streaming zipformer2 CTC

* Kotlin API for streaming zipformer2 CTC

* Golang API for streaming zipformer2 CTC

* C# API for streaming zipformer2 CTC

* Release v1.9.6
This commit is contained in:
Fangjun Kuang
2023-12-22 13:46:33 +08:00
committed by GitHub
parent 7634f5f034
commit e475e750ac
70 changed files with 1517 additions and 211 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
kotlin-api-examples/Main.kt
View File

@@ -8,7 +8,8 @@ fun callback(samples: FloatArray): Unit {
fun main() {
testTts()
testAsr()
testAsr("transducer")
testAsr("zipformer2-ctc")
}
fun testTts() {
@@ -30,25 +31,43 @@ fun testTts() {
audio.save(filename="test-en.wav")
}
fun testAsr() {
fun testAsr(type: String) {
var featConfig = FeatureConfig(
sampleRate = 16000,
featureDim = 80,
)
// please refer to
// https://k2-fsa.github.io/sherpa/onnx/pretrained_models/index.html
// to dowload pre-trained models
var modelConfig = OnlineModelConfig(
transducer = OnlineTransducerModelConfig(
encoder = "./sherpa-onnx-streaming-zipformer-en-2023-02-21/encoder-epoch-99-avg-1.onnx",
decoder = "./sherpa-onnx-streaming-zipformer-en-2023-02-21/decoder-epoch-99-avg-1.onnx",
joiner = "./sherpa-onnx-streaming-zipformer-en-2023-02-21/joiner-epoch-99-avg-1.onnx",
),
tokens = "./sherpa-onnx-streaming-zipformer-en-2023-02-21/tokens.txt",
numThreads = 1,
debug = false,
)
var waveFilename: String
var modelConfig: OnlineModelConfig = when (type) {
"transducer" -> {
waveFilename = "./sherpa-onnx-streaming-zipformer-en-2023-02-21/test_wavs/0.wav"
// please refer to
// https://k2-fsa.github.io/sherpa/onnx/pretrained_models/index.html
// to dowload pre-trained models
OnlineModelConfig(
transducer = OnlineTransducerModelConfig(
encoder = "./sherpa-onnx-streaming-zipformer-en-2023-02-21/encoder-epoch-99-avg-1.onnx",
decoder = "./sherpa-onnx-streaming-zipformer-en-2023-02-21/decoder-epoch-99-avg-1.onnx",
joiner = "./sherpa-onnx-streaming-zipformer-en-2023-02-21/joiner-epoch-99-avg-1.onnx",
),
tokens = "./sherpa-onnx-streaming-zipformer-en-2023-02-21/tokens.txt",
numThreads = 1,
debug = false,
)
}
"zipformer2-ctc" -> {
waveFilename = "./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/DEV_T0000000000.wav"
OnlineModelConfig(
zipformer2Ctc = OnlineZipformer2CtcModelConfig(
model = "./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/ctc-epoch-20-avg-1-chunk-16-left-128.onnx",
),
tokens = "./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/tokens.txt",
numThreads = 1,
debug = false,
)
}
else -> throw IllegalArgumentException(type)
}
var endpointConfig = EndpointConfig()
@@ -69,7 +88,7 @@ fun testAsr() {
)
var objArray = WaveReader.readWaveFromFile(
filename = "./sherpa-onnx-streaming-zipformer-en-2023-02-21/test_wavs/0.wav",
filename = waveFilename,
)
var samples: FloatArray = objArray[0] as FloatArray
var sampleRate: Int = objArray[1] as Int

6
kotlin-api-examples/run.sh
View File

@@ -34,6 +34,12 @@ if [ ! -f ./sherpa-onnx-streaming-zipformer-en-2023-02-21/tokens.txt ]; then
git clone https://huggingface.co/csukuangfj/sherpa-onnx-streaming-zipformer-en-2023-02-21
fi
if [ ! -d ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13 ]; then
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13.tar.bz2
tar xvf sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13.tar.bz2
rm sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13.tar.bz2
fi
if [ ! -f ./vits-piper-en_US-amy-low/en_US-amy-low.onnx ]; then
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-piper-en_US-amy-low.tar.bz2
tar xf vits-piper-en_US-amy-low.tar.bz2