Requirement 013 and its implementation: page-mic.js puts a microphone on every textarea and text input, records with MediaRecorder and inserts the transcript at the cursor; Escape cancels. /api/stt transcribes with the local whisper.cpp model ggml-small-q8_0 (pinned to commit 5359861c and its sha256) in a per-request temp dir, capped at 60 s and 5 MiB, and returns German or English only, retranscribing a clip detected as another language in both and keeping the surer one. Without a model the button is disabled and names the install row. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14). 🎯 Fix: 72 % 💥 Break: 12 % 💸 Tokens: – ⏱️ Velocity: – 🛡️ Security: 100 % 🏆 Score: 63 🚦 Gate: ⛔ fix 72 % < 90, break 12 % > 5 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
76 lines
3.3 KiB
Python
76 lines
3.3 KiB
Python
from __future__ import annotations
|
|
|
|
import io
|
|
import json
|
|
import sys
|
|
import wave
|
|
from pathlib import Path
|
|
|
|
from hub_support import server
|
|
|
|
VOICES = ["de_DE-solo-medium:0", "en_US-test-high:0", "en_US-test-high:1", "en_US-test-high:2", "en_US-test-high:3"]
|
|
OPERATOR_VOICE = "en_US-test-high:0"
|
|
FAKE_PIPER = """
|
|
import argparse, json, os, sys, wave
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--model", required=True)
|
|
parser.add_argument("--config", required=True)
|
|
parser.add_argument("--output-file", required=True)
|
|
parser.add_argument("--speaker", type=int)
|
|
args = parser.parse_args()
|
|
text = sys.stdin.read()
|
|
with open(os.path.join(os.environ["HOME"], "piper.jsonl"), "a", encoding="utf-8") as log:
|
|
log.write(json.dumps({"argv": sys.argv[1:], "text": text, "tmp": os.environ["TMPDIR"], "cwd": os.getcwd()}) + "\\n")
|
|
if "FAIL" in text:
|
|
sys.exit(3)
|
|
with wave.open(args.output_file, "wb") as out:
|
|
out.setnchannels(1)
|
|
out.setsampwidth(2)
|
|
out.setframerate(22050)
|
|
out.writeframes(bytes(2 * len(text)))
|
|
"""
|
|
FAKE_WHISPER = """
|
|
import json, os, sys
|
|
argv = sys.argv[1:]
|
|
data = sys.stdin.buffer.read()
|
|
with open(os.path.join(os.environ["HOME"], "whisper.jsonl"), "a", encoding="utf-8") as log:
|
|
log.write(json.dumps({"argv": argv, "sha256": __import__("hashlib").sha256(data).hexdigest()}) + "\\n")
|
|
if b"FAIL" in data:
|
|
sys.exit(4)
|
|
language = argv[argv.index("--language") + 1]
|
|
segments = [{"text": " hello from the [BLANK_AUDIO] mic", "tokens": [{"text": "[_BEG_]", "p": 0.1}, {"text": " hello", "p": 0.9}]}, {"text": "second line", "tokens": [{"text": " second", "p": 0.8}]}]
|
|
with open(argv[argv.index("--output-file") + 1] + ".json", "w", encoding="utf-8") as out:
|
|
json.dump({"result": {"language": "en" if language == "auto" else language}, "transcription": segments}, out)
|
|
"""
|
|
|
|
|
|
def write_engines(base: Path) -> server.Engines:
|
|
bin_dir, voices, scratch = base / "bin", base / "voices", base / "scratch"
|
|
for folder in (bin_dir, voices, scratch):
|
|
folder.mkdir()
|
|
for name, body in (("piper", FAKE_PIPER), ("whisper-cli", FAKE_WHISPER)):
|
|
path = bin_dir / name
|
|
path.write_text(f"#!{sys.executable}\n{body}", encoding="utf-8")
|
|
path.chmod(0o755)
|
|
for model, config in (("en_US-test-high", {"num_speakers": 4}), ("de_DE-solo-medium", {"num_speakers": 1}), ("zero", {"num_speakers": 0}), ("bad name!", {"num_speakers": 2})):
|
|
(voices / f"{model}.onnx").write_bytes(b"onnx")
|
|
(voices / f"{model}.onnx.json").write_text(json.dumps(config), encoding="utf-8")
|
|
(voices / "broken.onnx").write_bytes(b"onnx")
|
|
model = base / "ggml-small-q8_0.bin"
|
|
model.write_bytes(b"ggml")
|
|
return server.Engines(piper=bin_dir / "piper", voices=voices, operator_voice=OPERATOR_VOICE, whisper=bin_dir / "whisper-cli", whisper_model=model, scratch=scratch, service=server.Service(url="", key=""))
|
|
|
|
|
|
def wav_bytes(channels: int, width: int, rate: int, frames: bytes) -> bytes:
|
|
buffer = io.BytesIO()
|
|
with wave.open(buffer, "wb") as writer:
|
|
writer.setnchannels(channels)
|
|
writer.setsampwidth(width)
|
|
writer.setframerate(rate)
|
|
writer.writeframes(frames)
|
|
return buffer.getvalue()
|
|
|
|
|
|
def log_rows(path: Path) -> list[dict]:
|
|
return [json.loads(line) for line in path.read_text(encoding="utf-8").splitlines()] if path.is_file() else []
|