音频和 DeepSpeech

Question

我为 wav 文件测试了 DeepSpeech，它工作正常。当我尝试使用无法识别单个单词的音频流时，我的深度语音问题就出现了。音频流是 PCM 48khz 立体声签名的 16 位小端序。我一直在尝试将流转换为其他格式、sampleRate 和频道，但完全没有成功。我在 nodejs 上使用 DeepSpeech

 modelStream = englishModel.createStream();

    let chunks = [];
    stream.on('data', chunk => {
        chunks.push(chunk);

    }).on('close', () => {
        const buffer = Buffer.concat(chunks);


        let stream = new Duplex();
        stream.push(buffer);
        stream.push(null);
        let audioStream = new MemoryStream();
        stream.pipe(Sox({
            global: {
                'no-dither': true,
            },
            output: {
                bits: 16,
                rate: desiredSampleRate,
                channels: 1,
                encoding: 'signed-integer',
                endian: 'little',
                compression: 0.0,
                type: 'raw'
            }
        })).
        pipe(audioStream);

        audioStream.on('finish', () => {
            let audioBuffer = audioStream.toBuffer();

            const audioLength = (audioBuffer.length / 2) * (1 / desiredSampleRate);
            console.log('audio length', audioLength);

            let result = englishModel.stt(audioBuffer);

            console.log('result:', result);
        });

Answer 1

您正在尝试将流提供给需要 wav 文件的方法...

请改用modelStream.feedAudioContent();。 Check the example.