使用Go,我正在使用RTMP流,将其转码为FLAC(使用ffmpeg)并尝试流式传输到Google的Speech API以转录音频。但是,我在发送数据时遇到EOF
错误。我在文档中找不到关于此错误的任何信息,因此我不确定是什么导致它。
我正在将收到的数据分块为3s片段(长度不相关,只要它小于流识别请求的最大长度)。
以下是我的代码的核心:
func main() {
done := make(chan os.Signal)
received := make(chan []byte)
go receive(received)
go transcribe(received)
signal.Notify(done, os.Interrupt, syscall.SIGTERM)
select {
case <-done:
os.Exit(0)
}
}
func receive(received chan<- []byte) {
var b bytes.Buffer
stdout := bufio.NewWriter(&b)
cmd := exec.Command("ffmpeg", "-i", "rtmp://127.0.0.1:1935/live/key", "-f", "flac", "-ar", "16000", "-")
cmd.Stdout = stdout
if err := cmd.Start(); err != nil {
log.Fatal(err)
}
duration, _ := time.ParseDuration("3s")
ticker := time.NewTicker(duration)
for {
select {
case <-ticker.C:
stdout.Flush()
log.Printf("Received %d bytes", b.Len())
received <- b.Bytes()
b.Reset()
}
}
}
func transcribe(received <-chan []byte) {
ctx := context.TODO()
client, err := speech.NewClient(ctx)
if err != nil {
log.Fatal(err)
}
stream, err := client.StreamingRecognize(ctx)
if err != nil {
log.Fatal(err)
}
// Send the initial configuration message.
if err = stream.Send(&speechpb.StreamingRecognizeRequest{
StreamingRequest: &speechpb.StreamingRecognizeRequest_StreamingConfig{
StreamingConfig: &speechpb.StreamingRecognitionConfig{
Config: &speechpb.RecognitionConfig{
Encoding: speechpb.RecognitionConfig_FLAC,
LanguageCode: "en-GB",
SampleRateHertz: 16000,
},
},
},
}); err != nil {
log.Fatal(err)
}
for {
select {
case data := <-received:
if len(data) > 0 {
log.Printf("Sending %d bytes", len(data))
if err := stream.Send(&speechpb.StreamingRecognizeRequest{
StreamingRequest: &speechpb.StreamingRecognizeRequest_AudioContent{
AudioContent: data,
},
}); err != nil {
log.Printf("Could not send audio: %v", err)
}
}
}
}
}
运行此代码会提供此输出:
2017/10/09 16:05:00 Received 191704 bytes
2017/10/09 16:05:00 Saving 191704 bytes
2017/10/09 16:05:00 Sending 191704 bytes
2017/10/09 16:05:00 Could not send audio: EOF
2017/10/09 16:05:03 Received 193192 bytes
2017/10/09 16:05:03 Saving 193192 bytes
2017/10/09 16:05:03 Sending 193192 bytes
2017/10/09 16:05:03 Could not send audio: EOF
2017/10/09 16:05:06 Received 193188 bytes
2017/10/09 16:05:06 Saving 193188 bytes
2017/10/09 16:05:06 Sending 193188 bytes // Notice that this doesn't error
2017/10/09 16:05:09 Received 191704 bytes
2017/10/09 16:05:09 Saving 191704 bytes
2017/10/09 16:05:09 Sending 191704 bytes
2017/10/09 16:05:09 Could not send audio: EOF
请注意,并非所有Send
都失败。
有人能指出我在正确的方向吗?它与FLAC标题或其他东西有关吗?我也想知道是否重置缓冲区会导致某些数据被丢弃(即这是一项非常重要的操作,实际上需要一些时间才能完成)并且它不喜欢这些缺少的信息?
任何帮助都会非常感激。
答案 0 :(得分:7)
因此,事实证明,这是一种获取有关流状态的更多信息的方法,因此我们不必依赖返回的错误。
if err := stream.Send(&speechpb.StreamingRecognizeRequest{
StreamingRequest: &speechpb.StreamingRecognizeRequest_AudioContent{
AudioContent: data,
},
}); err != nil {
resp, err := stream.Recv()
log.Printf("Could not send audio: %v", resp.GetError())
}
打印:
2017/10/16 17:14:53 Could not send audio: code:3 message:"Invalid audio content: too long."
哪一个更有用的错误消息!