fe4bd59248
Replace @xenova/transformers in-process model with HTTP calls to shared whisper-asr-webservice container (http://whisper:9000). Converts PCM16 samples to WAV and sends to /asr endpoint. Env: WHISPER_URL.
70 lines
2.2 KiB
TypeScript
70 lines
2.2 KiB
TypeScript
type WhisperTranscribeInput = {
|
|
samples: Float32Array;
|
|
sampleRate: number;
|
|
language?: string;
|
|
};
|
|
|
|
function getWhisperUrl() {
|
|
return (process.env.WHISPER_URL ?? "http://whisper:9000").replace(/\/+$/, "");
|
|
}
|
|
|
|
function getWhisperLanguage() {
|
|
const value = (process.env.CF_WHISPER_LANGUAGE ?? "ru").trim();
|
|
return value || "ru";
|
|
}
|
|
|
|
function pcmToWav(samples: Float32Array, sampleRate: number): Buffer {
|
|
const numChannels = 1;
|
|
const bitsPerSample = 16;
|
|
const byteRate = sampleRate * numChannels * (bitsPerSample / 8);
|
|
const blockAlign = numChannels * (bitsPerSample / 8);
|
|
const dataSize = samples.length * (bitsPerSample / 8);
|
|
const headerSize = 44;
|
|
const buffer = Buffer.alloc(headerSize + dataSize);
|
|
|
|
// RIFF header
|
|
buffer.write("RIFF", 0);
|
|
buffer.writeUInt32LE(36 + dataSize, 4);
|
|
buffer.write("WAVE", 8);
|
|
|
|
// fmt chunk
|
|
buffer.write("fmt ", 12);
|
|
buffer.writeUInt32LE(16, 16);
|
|
buffer.writeUInt16LE(1, 20); // PCM
|
|
buffer.writeUInt16LE(numChannels, 22);
|
|
buffer.writeUInt32LE(sampleRate, 24);
|
|
buffer.writeUInt32LE(byteRate, 28);
|
|
buffer.writeUInt16LE(blockAlign, 32);
|
|
buffer.writeUInt16LE(bitsPerSample, 34);
|
|
|
|
// data chunk
|
|
buffer.write("data", 36);
|
|
buffer.writeUInt32LE(dataSize, 40);
|
|
|
|
for (let i = 0; i < samples.length; i += 1) {
|
|
const s = Math.max(-1, Math.min(1, samples[i] ?? 0));
|
|
const val = s < 0 ? s * 0x8000 : s * 0x7fff;
|
|
buffer.writeInt16LE(Math.round(val), headerSize + i * 2);
|
|
}
|
|
|
|
return buffer;
|
|
}
|
|
|
|
export async function transcribeWithWhisper(input: WhisperTranscribeInput) {
|
|
const wav = pcmToWav(input.samples, input.sampleRate);
|
|
const language = (input.language ?? getWhisperLanguage()) || "ru";
|
|
const url = `${getWhisperUrl()}/asr?task=transcribe&language=${language}&output=json`;
|
|
|
|
const formData = new FormData();
|
|
formData.append("audio_file", new Blob([wav], { type: "audio/wav" }), "audio.wav");
|
|
|
|
const response = await fetch(url, { method: "POST", body: formData });
|
|
if (!response.ok) {
|
|
const detail = await response.text().catch(() => "");
|
|
throw new Error(`Whisper service error ${response.status}: ${detail}`);
|
|
}
|
|
|
|
const result = (await response.json()) as { text?: string };
|
|
return String(result?.text ?? "").trim();
|
|
}
|