Add Go API for TTS (#377)

This commit is contained in:
Fangjun Kuang
2023-10-20 15:57:52 +08:00
committed by GitHub
parent 3ba9a4932f
commit a69d0a950e
23 changed files with 400 additions and 108 deletions

View File

@@ -1,9 +1,3 @@
module non-streaming-decode-files
go 1.12
require (
github.com/k2-fsa/sherpa-onnx-go v1.7.12-alpha
github.com/spf13/pflag v1.0.5
github.com/youpy/go-wav v0.3.2
)

View File

@@ -1,35 +0,0 @@
github.com/davecgh/go-spew v1.1.0 h1:ZDRjVQ15GmhC3fiQ8ni8+OwkZQO4DARzQgrnXU1Liz8=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/google/go-cmp v0.5.6 h1:BKbKCqvP6I+rmFHt06ZmyQtvB8xAkWdhFyr0ZUNZcxQ=
github.com/google/go-cmp v0.5.6/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/k2-fsa/sherpa-onnx-go v1.7.12-alpha h1:pm9VCFe51c59LilgDmGwKGfGB/TalLJX26LSvjrELTk=
github.com/k2-fsa/sherpa-onnx-go v1.7.12-alpha/go.mod h1:JLAytuKK2r1sPf8BcyaUTFfvmGGTLpbfG9g9x/Rq7GA=
github.com/k2-fsa/sherpa-onnx-go-linux v1.7.12 h1:9g6Af3kBtcbDrTH7EqlWB9cSvBsc/xY00r7MeA/qVzo=
github.com/k2-fsa/sherpa-onnx-go-linux v1.7.12/go.mod h1:lHZRU/WtBUJetJVPyXHg092diEWYyIEoaob+LMJKWvo=
github.com/k2-fsa/sherpa-onnx-go-macos v1.7.12-alpha h1:G8B6PaPHTFlbe6YtUFc7/H4rJfzmOJRvEzPJMj4h/w8=
github.com/k2-fsa/sherpa-onnx-go-macos v1.7.12-alpha/go.mod h1:o1Cd6Zy+Tpq3bLAWqBoVcDenxi8HSaSubURtbtIqH2s=
github.com/k2-fsa/sherpa-onnx-go-windows v1.7.12 h1:WudeR8tlCsS5uj0d99jJ+jaKjvyND+aCuajFDE9qEY4=
github.com/k2-fsa/sherpa-onnx-go-windows v1.7.12/go.mod h1:R7JSrFkZGkfM/F/gVSR+yTJ+sPaHhJgdqsB5N7dTU6E=
github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/testify v1.6.1 h1:hDPOHmpOpP40lSULcqw7IrRb/u7w6RpDC9399XyoNd0=
github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/youpy/go-riff v0.1.0 h1:vZO/37nI4tIET8tQI0Qn0Y79qQh99aEpponTPiPut7k=
github.com/youpy/go-riff v0.1.0/go.mod h1:83nxdDV4Z9RzrTut9losK7ve4hUnxUR8ASSz4BsKXwQ=
github.com/youpy/go-wav v0.3.2 h1:NLM8L/7yZ0Bntadw/0h95OyUsen+DQIVf9gay+SUsMU=
github.com/youpy/go-wav v0.3.2/go.mod h1:0FCieAXAeSdcxFfwLpRuEo0PFmAoc+8NU34h7TUvk50=
github.com/zaf/g711 v0.0.0-20190814101024-76a4a538f52b h1:QqixIpc5WFIqTLxB3Hq8qs0qImAgBdq0p6rq2Qdl634=
github.com/zaf/g711 v0.0.0-20190814101024-76a4a538f52b/go.mod h1:T2h1zV50R/q0CVYnsQOQ6L7P4a2ZxH47ixWcMXFGyx8=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543 h1:E7g+9GITq07hpfrRu66IVDexMakfv52eLZ2CXBWiKr4=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c h1:dUUwHk2QECo/6vqA44rthZ8ie2QXMNeKRTHCNY2nXvo=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gotest.tools v2.2.0+incompatible h1:VsBPFP1AI068pPrMxtb/S8Zkgf9xEmTLJjfM+P5UIEo=
gotest.tools v2.2.0+incompatible/go.mod h1:DsYFclhRJ6vuDpmuTbkuFWG+y2sxOXAzmJt81HFBacw=

View File

@@ -0,0 +1,3 @@
module non-streaming-tts
go 1.12

View File

@@ -0,0 +1,61 @@
package main
import (
sherpa "github.com/k2-fsa/sherpa-onnx-go/sherpa_onnx"
flag "github.com/spf13/pflag"
"log"
)
func main() {
log.SetFlags(log.LstdFlags | log.Lmicroseconds)
config := sherpa.OfflineTtsConfig{}
sid := 0
filename := "./generated.wav"
flag.StringVar(&config.Model.Vits.Model, "vits-model", "", "Path to the vits ONNX model")
flag.StringVar(&config.Model.Vits.Lexicon, "vits-lexicon", "", "Path to lexicon.txt")
flag.StringVar(&config.Model.Vits.Tokens, "vits-tokens", "", "Path to tokens.txt")
flag.Float32Var(&config.Model.Vits.NoiseScale, "vits-noise-scale", 0.667, "noise_scale for VITS")
flag.Float32Var(&config.Model.Vits.NoiseScaleW, "vits-noise-scale-w", 0.8, "noise_scale_w for VITS")
flag.Float32Var(&config.Model.Vits.LengthScale, "vits-length-scale", 1.0, "length_scale for VITS. small -> faster in speech speed; large -> slower")
flag.IntVar(&config.Model.NumThreads, "num-threads", 1, "Number of threads for computing")
flag.IntVar(&config.Model.Debug, "debug", 0, "Whether to show debug message")
flag.StringVar(&config.Model.Provider, "provider", "cpu", "Provider to use")
flag.IntVar(&sid, "sid", 0, "Speaker ID. Used only for multi-speaker models")
flag.StringVar(&filename, "output-filename", "./generated.wav", "Filename to save the generated audio")
flag.Parse()
if len(flag.Args()) != 1 {
log.Fatalf("Please provide the text to generate audios")
}
text := flag.Arg(0)
log.Println("Input text:", text)
log.Println("Speaker ID:", sid)
log.Println("Output filename:", filename)
log.Println("Initializing model (may take several seconds)")
tts := sherpa.NewOfflineTts(&config)
defer sherpa.DeleteOfflineTts(tts)
log.Println("Model created!")
log.Println("Start generating!")
audio := tts.Generate(text, sid)
log.Println("Done!")
ok := audio.Save(filename)
if ok != 1 {
log.Fatalf("Failed to write", filename)
}
}

View File

@@ -0,0 +1,14 @@
#!/usr/bin/env bash
# please refer to
# https://k2-fsa.github.io/sherpa/onnx/tts/pretrained_models/vits.html#ljspeech-english-single-speaker
# to download the model before you run this script
./non-streaming-tts \
--vits-model=./vits-ljs/vits-ljs.onnx \
--vits-lexicon=./vits-ljs/lexicon.txt \
--vits-tokens=./vits-ljs/tokens.txt \
--sid=0 \
--debug=1 \
--output-filename=./vits-ljs.wav \
"Liliana, the most beautiful and lovely assistant of our team!"

View File

@@ -0,0 +1,16 @@
#!/usr/bin/env bash
# please refer to
# https://k2-fsa.github.io/sherpa/onnx/tts/pretrained_models/vits.html#vctk-english-multi-speaker-109-speakers
# to download the model before you run this script
for sid in 0 10 108; do
./non-streaming-tts \
--vits-model=./vits-vctk/vits-vctk.onnx \
--vits-lexicon=./vits-vctk/lexicon.txt \
--vits-tokens=./vits-vctk/tokens.txt \
--sid=0 \
--debug=1 \
--output-filename=./kennedy-$sid.wav \
'Ask not what your country can do for you; ask what you can do for your country.'
done

View File

@@ -0,0 +1,16 @@
#!/usr/bin/env bash
# please refer to
# https://k2-fsa.github.io/sherpa/onnx/tts/pretrained_models/vits.html#aishell3-chinese-multi-speaker-174-speakers
# to download the model before you run this script
for sid in 10 33 99; do
./non-streaming-tts \
--vits-model=./vits-zh-aishell3/vits-aishell3.onnx \
--vits-lexicon=./vits-zh-aishell3/lexicon.txt \
--vits-tokens=./vits-zh-aishell3/tokens.txt \
--sid=10 \
--debug=1 \
--output-filename=./liliana-$sid.wav \
"林美丽最美丽、最漂亮、最可爱!"
done

View File

@@ -1,9 +1,3 @@
module real-time-speech-recognition-from-microphone
go 1.12
require (
github.com/gordonklaus/portaudio v0.0.0-20230709114228-aafa478834f5
github.com/k2-fsa/sherpa-onnx-go v1.7.12-alpha
github.com/spf13/pflag v1.0.5
)

View File

@@ -1,12 +0,0 @@
github.com/gordonklaus/portaudio v0.0.0-20230709114228-aafa478834f5 h1:5AlozfqaVjGYGhms2OsdUyfdJME76E6rx5MdGpjzZpc=
github.com/gordonklaus/portaudio v0.0.0-20230709114228-aafa478834f5/go.mod h1:WY8R6YKlI2ZI3UyzFk7P6yGSuS+hFwNtEzrexRyD7Es=
github.com/k2-fsa/sherpa-onnx-go v1.7.12-alpha h1:pm9VCFe51c59LilgDmGwKGfGB/TalLJX26LSvjrELTk=
github.com/k2-fsa/sherpa-onnx-go v1.7.12-alpha/go.mod h1:JLAytuKK2r1sPf8BcyaUTFfvmGGTLpbfG9g9x/Rq7GA=
github.com/k2-fsa/sherpa-onnx-go-linux v1.7.12 h1:9g6Af3kBtcbDrTH7EqlWB9cSvBsc/xY00r7MeA/qVzo=
github.com/k2-fsa/sherpa-onnx-go-linux v1.7.12/go.mod h1:lHZRU/WtBUJetJVPyXHg092diEWYyIEoaob+LMJKWvo=
github.com/k2-fsa/sherpa-onnx-go-macos v1.7.12-alpha h1:G8B6PaPHTFlbe6YtUFc7/H4rJfzmOJRvEzPJMj4h/w8=
github.com/k2-fsa/sherpa-onnx-go-macos v1.7.12-alpha/go.mod h1:o1Cd6Zy+Tpq3bLAWqBoVcDenxi8HSaSubURtbtIqH2s=
github.com/k2-fsa/sherpa-onnx-go-windows v1.7.12 h1:WudeR8tlCsS5uj0d99jJ+jaKjvyND+aCuajFDE9qEY4=
github.com/k2-fsa/sherpa-onnx-go-windows v1.7.12/go.mod h1:R7JSrFkZGkfM/F/gVSR+yTJ+sPaHhJgdqsB5N7dTU6E=
github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=

View File

@@ -1,9 +1,3 @@
module streaming-decode-files
go 1.12
require (
github.com/k2-fsa/sherpa-onnx-go v1.7.12-alpha
github.com/spf13/pflag v1.0.5
github.com/youpy/go-wav v0.3.2
)

View File

@@ -1,35 +0,0 @@
github.com/davecgh/go-spew v1.1.0 h1:ZDRjVQ15GmhC3fiQ8ni8+OwkZQO4DARzQgrnXU1Liz8=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/google/go-cmp v0.5.6 h1:BKbKCqvP6I+rmFHt06ZmyQtvB8xAkWdhFyr0ZUNZcxQ=
github.com/google/go-cmp v0.5.6/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/k2-fsa/sherpa-onnx-go v1.7.12-alpha h1:pm9VCFe51c59LilgDmGwKGfGB/TalLJX26LSvjrELTk=
github.com/k2-fsa/sherpa-onnx-go v1.7.12-alpha/go.mod h1:JLAytuKK2r1sPf8BcyaUTFfvmGGTLpbfG9g9x/Rq7GA=
github.com/k2-fsa/sherpa-onnx-go-linux v1.7.12 h1:9g6Af3kBtcbDrTH7EqlWB9cSvBsc/xY00r7MeA/qVzo=
github.com/k2-fsa/sherpa-onnx-go-linux v1.7.12/go.mod h1:lHZRU/WtBUJetJVPyXHg092diEWYyIEoaob+LMJKWvo=
github.com/k2-fsa/sherpa-onnx-go-macos v1.7.12-alpha h1:G8B6PaPHTFlbe6YtUFc7/H4rJfzmOJRvEzPJMj4h/w8=
github.com/k2-fsa/sherpa-onnx-go-macos v1.7.12-alpha/go.mod h1:o1Cd6Zy+Tpq3bLAWqBoVcDenxi8HSaSubURtbtIqH2s=
github.com/k2-fsa/sherpa-onnx-go-windows v1.7.12 h1:WudeR8tlCsS5uj0d99jJ+jaKjvyND+aCuajFDE9qEY4=
github.com/k2-fsa/sherpa-onnx-go-windows v1.7.12/go.mod h1:R7JSrFkZGkfM/F/gVSR+yTJ+sPaHhJgdqsB5N7dTU6E=
github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/testify v1.6.1 h1:hDPOHmpOpP40lSULcqw7IrRb/u7w6RpDC9399XyoNd0=
github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/youpy/go-riff v0.1.0 h1:vZO/37nI4tIET8tQI0Qn0Y79qQh99aEpponTPiPut7k=
github.com/youpy/go-riff v0.1.0/go.mod h1:83nxdDV4Z9RzrTut9losK7ve4hUnxUR8ASSz4BsKXwQ=
github.com/youpy/go-wav v0.3.2 h1:NLM8L/7yZ0Bntadw/0h95OyUsen+DQIVf9gay+SUsMU=
github.com/youpy/go-wav v0.3.2/go.mod h1:0FCieAXAeSdcxFfwLpRuEo0PFmAoc+8NU34h7TUvk50=
github.com/zaf/g711 v0.0.0-20190814101024-76a4a538f52b h1:QqixIpc5WFIqTLxB3Hq8qs0qImAgBdq0p6rq2Qdl634=
github.com/zaf/g711 v0.0.0-20190814101024-76a4a538f52b/go.mod h1:T2h1zV50R/q0CVYnsQOQ6L7P4a2ZxH47ixWcMXFGyx8=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543 h1:E7g+9GITq07hpfrRu66IVDexMakfv52eLZ2CXBWiKr4=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c h1:dUUwHk2QECo/6vqA44rthZ8ie2QXMNeKRTHCNY2nXvo=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gotest.tools v2.2.0+incompatible h1:VsBPFP1AI068pPrMxtb/S8Zkgf9xEmTLJjfM+P5UIEo=
gotest.tools v2.2.0+incompatible/go.mod h1:DsYFclhRJ6vuDpmuTbkuFWG+y2sxOXAzmJt81HFBacw=