Live streaming recognition
- Print
- PDF
Live streaming recognition
- Print
- PDF
Article summary
Did you find this summary helpful?
Thank you for your feedback
Available in Classic and VPC
This document introduces live streaming examples from the CLOVA Speech service.
Java
The following is a Java-based sample code for the API.
Project Structure
├───pom.xml │ │ └───src │ ├───main │ │ ├───java │ │ │ └───com │ │ │ └───example │ │ │ └───grpc │ │ │ GRpcClient.java │ │ │ │ │ ├───proto │ │ │ nest.proto
pom.xml
<?xml version="1.0" encoding="UTF-8"?> <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> <modelVersion>4.0.0</modelVersion> <groupId>com.example</groupId> <artifactId>clova-speech-grpc</artifactId> <version>1.0-SNAPSHOT</version> <properties> <java.version>1.8</java.version> <maven.compiler.source>${java.version}</maven.compiler.source> <maven.compiler.target>${java.version}</maven.compiler.target> <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding> <netty.version>4.1.52.Final</netty.version> <grpc.version>1.35.0</grpc.version> <protoc.version>3.14.0</protoc.version> </properties> <dependencies> <dependency> <groupId>io.grpc</groupId> <artifactId>grpc-netty</artifactId> <version>${grpc.version}</version> </dependency> <dependency> <groupId>io.grpc</groupId> <artifactId>grpc-netty-shaded</artifactId> <version>${grpc.version}</version> </dependency> <dependency> <groupId>io.grpc</groupId> <artifactId>grpc-protobuf</artifactId> <version>${grpc.version}</version> </dependency> <dependency> <groupId>io.grpc</groupId> <artifactId>grpc-stub</artifactId> <version>${grpc.version}</version> </dependency> <dependency> <groupId>org.projectlombok</groupId> <artifactId>lombok</artifactId> <optional>true</optional> <version>1.18.12</version> </dependency> </dependencies> <build> <extensions> <extension> <groupId>kr.motd.maven</groupId> <artifactId>os-maven-plugin</artifactId> <version>1.6.1</version> </extension> </extensions> <plugins> <plugin> <groupId>org.apache.maven.plugins</groupId> <artifactId>maven-compiler-plugin</artifactId> <version>3.1</version> <executions> <execution> <id>compile</id> <phase>compile</phase> <goals> <goal>compile</goal> </goals> </execution> <execution> <id>testCompile</id> <phase>test-compile</phase> <goals> <goal>testCompile</goal> </goals> </execution> </executions> <configuration> <showDeprecation>true</showDeprecation> <encoding>${project.build.sourceEncoding}</encoding> </configuration> </plugin> <plugin> <groupId>org.xolstice.maven.plugins</groupId> <artifactId>protobuf-maven-plugin</artifactId> <version>0.6.1</version> <configuration> <protocArtifact> com.google.protobuf:protoc:${protoc.version}:exe:${os.detected.classifier} </protocArtifact> <pluginId>grpc-java</pluginId> <pluginArtifact> io.grpc:protoc-gen-grpc-java:${grpc.version}:exe:${os.detected.classifier} </pluginArtifact> </configuration> <executions> <execution> <goals> <goal>compile</goal> <goal>compile-custom</goal> </goals> </execution> </executions> </plugin> </plugins> </build> </project>
Java
package com.example.grpc; import java.io.FileInputStream; import java.util.concurrent.CountDownLatch; import com.google.protobuf.ByteString; import com.nbp.cdncp.nest.grpc.proto.v1.NestConfig; import com.nbp.cdncp.nest.grpc.proto.v1.NestData; import com.nbp.cdncp.nest.grpc.proto.v1.NestRequest; import com.nbp.cdncp.nest.grpc.proto.v1.NestResponse; import com.nbp.cdncp.nest.grpc.proto.v1.NestServiceGrpc; import com.nbp.cdncp.nest.grpc.proto.v1.RequestType; import io.grpc.ManagedChannel; import io.grpc.Metadata; import io.grpc.StatusRuntimeException; import io.grpc.netty.NettyChannelBuilder; import io.grpc.stub.MetadataUtils; import io.grpc.stub.StreamObserver; public class GRpcClient { public static void main(String[] args) throws Exception { CountDownLatch latch = new CountDownLatch(1); ManagedChannel channel = NettyChannelBuilder .forTarget("clovaspeech-gw.ncloud.com:50051") .useTransportSecurity() .build(); NestServiceGrpc.NestServiceStub client = NestServiceGrpc.newStub(channel); Metadata metadata = new Metadata(); metadata.put(Metadata.Key.of("Authorization", Metadata.ASCII_STRING_MARSHALLER), "Bearer ${secretKey}"); client = MetadataUtils.attachHeaders(client, metadata); StreamObserver<NestResponse> responseObserver = new StreamObserver<NestResponse>() { @Override public void onNext(NestResponse response) { System.out.println("Received response: " + response.getContents()); } @Override public void onError(Throwable t) { if(t instanceof StatusRuntimeException) { StatusRuntimeException error = (StatusRuntimeException)t; System.out.println(error.getStatus().getDescription()); } latch.countDown(); } @Override public void onCompleted() { System.out.println("completed"); latch.countDown(); } }; StreamObserver<NestRequest> requestObserver = client.recognize(responseObserver); requestObserver.onNext(NestRequest.newBuilder() .setType(RequestType.CONFIG) .setConfig(NestConfig.newBuilder() .setConfig("{\"transcription\":{\"language\":\"ko\"}}") .build()) .build()); java.io.File file = new java.io.File("~/media/42s.wav"); byte[] buffer = new byte[32000]; int bytesRead; FileInputStream inputStream = new FileInputStream(file); while ((bytesRead = inputStream.read(buffer)) != -1) { requestObserver.onNext(NestRequest.newBuilder() .setType(RequestType.DATA) .setData(NestData.newBuilder() .setChunk(ByteString.copyFrom(buffer, 0, bytesRead)) .setExtraContents("{ \"seqId\": 0, \"epFlag\": false}") .build()) .build()); } requestObserver.onCompleted(); latch.await(); channel.shutdown(); } }
Python
The following is a Python-based sample code for the API.
import grpc
import json
import nest_pb2
import nest_pb2_grpc
AUDIO_PATH = "path/to/audio/file" #Enter the path to the audio file to be recognized. (PCM (headerless raw wave) format at 16 kHz, 1 channel, 16 bits per sample)
CLIENT_SECRET = "Long sentence recognition secretKey"
def generate_requests(audio_path):
# Initial setup request: set up speech recognition
yield nest_pb2.NestRequest(
type=nest_pb2.RequestType.CONFIG,
config=nest_pb2.NestConfig(
config=json.dumps({"transcription": {"language": "ko"}})
)
)
# Open an audio file and read 32,000 bytes at a time
with open(audio_path, "rb") as audio_file:
while True:
chunk = audio_file.read(32000) # Read chunks of an audio file
if not chunk:
break # Exit the loop when there is no more data
yield nest_pb2.NestRequest(
type=nest_pb2.RequestType.DATA,
data=nest_pb2.NestData(
chunk=chunk,
extra_contents=json.dumps({"seqId": 0, "epFlag": False})
)
)
def main():
# Set up a secure gRPC channel to the CLOVA Speech server
channel = grpc.secure_channel(
"clovaspeech-gw.ncloud.com:50051",
grpc.ssl_channel_credentials()
)
stub = nest_pb2_grpc.NestServiceStub(channel) # Create a stub for NestService
metadata = (("authorization", f"Bearer {CLIENT_SECRET}"),) # Set up metadata with authentication tokens
responses = stub.recognize(generate_requests(AUDIO_PATH), metadata=metadata) # Call the recognize method with the generated request
try:
# Process responses from the server repeatedly
for response in responses:
print("Received response: " + response.contents)
except grpc.RpcError as e:
# Handle gRPC errors
print(f"Error: {e.details()}")
finally:
channel.close() # Close the channel when finished
if __name__ == "__main__":
main()
Was this article helpful?