79 lines
2.5 KiB
Python
79 lines
2.5 KiB
Python
|
"""
|
||
|
|
Generate the W1 audio smoke dataset: a handful of 5s sine-wave clips paired
|
||
|
|
with deterministic transcripts.
|
||
|
|
|
||
|
|
Why synthetic instead of real speech: W1 only proves the forward path
|
||
|
|
(WhisperEncoder -> Projector -> GPT prepend) and that the projector's gradient
|
||
|
|
flows into a decreasing loss on a tiny fixed set. Real speech adds a network
|
||
|
|
dependency to a step that should be reproducible offline. W2 swaps in
|
||
|
|
LibriSpeech.
|
||
|
|
|
||
|
|
Audio files land under data/audio_smoke/wavs/ (gitignored). The manifest
|
||
|
|
data/audio_smoke/manifest.jsonl is the only artifact committed.
|
||
|
|
|
||
|
|
Usage:
|
||
|
|
python -m scripts.audio_smoke_data
|
||
|
|
"""
|
||
|
|
|
||
|
|
import argparse
|
||
|
|
import json
|
||
|
|
import wave
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
import numpy as np
|
||
|
|
|
||
|
|
|
||
|
|
SAMPLES = [
|
||
|
|
(220.0, "low tone"),
|
||
|
|
(330.0, "mid low tone"),
|
||
|
|
(440.0, "middle tone"),
|
||
|
|
(660.0, "mid high tone"),
|
||
|
|
(880.0, "high tone"),
|
||
|
|
]
|
||
|
|
SR = 16000
|
||
|
|
DURATION_S = 5.0
|
||
|
|
|
||
|
|
|
||
|
|
def synth_sine(freq_hz, duration_s=DURATION_S, sr=SR):
|
||
|
|
"""Sine + 2nd harmonic + a sliver of noise so Whisper sees non-degenerate
|
||
|
|
frames (a pure tone collapses to a near-constant log-mel)."""
|
||
|
|
t = np.arange(int(sr * duration_s)) / sr
|
||
|
|
x = 0.5 * np.sin(2 * np.pi * freq_hz * t) + 0.25 * np.sin(2 * np.pi * 2 * freq_hz * t)
|
||
|
|
rng = np.random.default_rng(int(freq_hz))
|
||
|
|
x = x + 0.01 * rng.standard_normal(len(x))
|
||
|
|
return x.astype(np.float32)
|
||
|
|
|
||
|
|
|
||
|
|
def write_wav_pcm16(path, audio, sr=SR):
|
||
|
|
"""Write mono PCM16 WAV using the stdlib (no scipy/soundfile dependency)."""
|
||
|
|
pcm = np.clip(audio, -1.0, 1.0)
|
||
|
|
pcm = (pcm * 32767.0).astype(np.int16)
|
||
|
|
with wave.open(str(path), "wb") as w:
|
||
|
|
w.setnchannels(1)
|
||
|
|
w.setsampwidth(2)
|
||
|
|
w.setframerate(sr)
|
||
|
|
w.writeframes(pcm.tobytes())
|
||
|
|
|
||
|
|
|
||
|
|
def generate_synthetic(data_dir):
|
||
|
|
data_dir = Path(data_dir)
|
||
|
|
wav_dir = data_dir / "wavs"
|
||
|
|
wav_dir.mkdir(parents=True, exist_ok=True)
|
||
|
|
manifest_path = data_dir / "manifest.jsonl"
|
||
|
|
with open(manifest_path, "w") as f:
|
||
|
|
for freq, text in SAMPLES:
|
||
|
|
name = f"sine_{int(freq):04d}.wav"
|
||
|
|
wav_path = wav_dir / name
|
||
|
|
if not wav_path.exists():
|
||
|
|
write_wav_pcm16(wav_path, synth_sine(freq))
|
||
|
|
f.write(json.dumps({"wav": f"wavs/{name}", "text": text, "sr": SR}) + "\n")
|
||
|
|
print(f"Wrote {len(SAMPLES)} samples to {data_dir}")
|
||
|
|
return manifest_path
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
parser = argparse.ArgumentParser()
|
||
|
|
parser.add_argument("--data-dir", default="data/audio_smoke")
|
||
|
|
args = parser.parse_args()
|
||
|
|
generate_synthetic(args.data_dir)
|