sherpa-ncnn：Linux(x86/ARM32/ARM64)构建sherpa-ncnn --语音转文本大模型

---

更多内容：XiaoJ的知识星球

---

---

1.构建sherpa-ncnn

x86构建：

git clone https://github.com/k2-fsa/sherpa-ncnn
cd sherpa-ncnn
mkdir build
cd build
cmake -DCMAKE_BUILD_TYPE=Release ..
make -j6

32-bit ARM构建:

git clone https://github.com/k2-fsa/sherpa-ncnn
cd sherpa-ncnn
mkdir build
cd build
cmake \-DCMAKE_BUILD_TYPE=Release \-DCMAKE_C_FLAGS="-march=armv7-a -mfloat-abi=hard -mfpu=neon" \-DCMAKE_CXX_FLAGS="-march=armv7-a -mfloat-abi=hard -mfpu=neon" \..
make -j6

64-bit ARM构建:

git clone https://github.com/k2-fsa/sherpa-ncnn
cd sherpa-ncnn
mkdir build
cd build
cmake \-DCMAKE_BUILD_TYPE=Release \-DCMAKE_C_FLAGS="-march=armv8-a" \-DCMAKE_CXX_FLAGS="-march=armv8-a" \..
make -j6

构建后，您将获得两个二进制文件：

• sherpa-ncnn：用于解码单个wav文件；

• sherpa-ncnn-alsa：用于通过读取带有 ALSA 的麦克风进行实时语音识别；

.

2.运行

请阅读 预训练模型 了解有关生成的二进制文件的用法。

2.1 运行sherpa-ncnn

单个语音文件解码测试

./sherpa-ncnn \
./tokens.txt \
./encoder_jit_trace-pnnx.ncnn.param \
./encoder_jit_trace-pnnx.ncnn.bin \
./decoder_jit_trace-pnnx.ncnn.param \
./decoder_jit_trace-pnnx.ncnn.bin \
./joiner_jit_trace-pnnx.ncnn.param \
./joiner_jit_trace-pnnx.ncnn.bin \
./1.wav \
3 \
greedy_search# 3：是指3个线程
# greedy_search：贪心搜索算法
# modified_beam_search：改进集束搜索算法

2.2 运行sherpa-ncnn-alsa

开发板上使用alsa架构从MIC说话测试。

./sherpa-ncnn-alsa \
./tokens.txt \
./encoder_jit_trace-pnnx.ncnn.param \
./encoder_jit_trace-pnnx.ncnn.bin \
./decoder_jit_trace-pnnx.ncnn.param \
./decoder_jit_trace-pnnx.ncnn.bin \
./joiner_jit_trace-pnnx.ncnn.param \
./joiner_jit_trace-pnnx.ncnn.bin \
"default" \
4 \
greedy_search# "default" ： 指定音频设备
#    使用命令查看：arecord -l
#    "plughw:<card,device>": 如"plughw:3,0"
# 3：是指3个线程
# greedy_search：贪心搜索算法
# modified_beam_search：改进集束搜索算法

测试输出：

[root@...:sherpa]# ./sherpa-ncnn-alsa ./tokens.txt ./encoder_
jit_trace-pnnx.ncnn.param ./encoder_jit_trace-pnnx.ncnn.bin ./decoder_jit_trace-
pnnx.ncnn.param ./decoder_jit_trace-pnnx.ncnn.bin ./joiner_jit_trace-pnnx.ncnn.p
aram ./joiner_jit_trace-pnnx.ncnn.bin "default" 4 greedy_search
...
Disable fp16 for Zipformer encoder
Don't Use GPU. has_gpu: 0, config.use_vulkan_compute: 1
Failed to set number of channels to 1. Invalid argument
Channel count is set to 2. Will use only 1 channel of it.
Current sample rate: 16000
Recording started!
Use recording device: default
0:这是一段测试^C
Caught Ctrl + C. Exiting...

.

---

声明：资源可能存在第三方来源，若有侵权请联系删除！