jpmschweitzerandClaude Fable 5
f5df5049db
- Face: new 'rage' state — 3-frame kaomoji loop (stare, flip the table, put it back) for in-flight request failures; 'error' stays the quiet persistent face for a dead link. Sim + artifact + design doc updated. - Gateway: stt.py/tts.py are now pluggable backends. Default 'speaches' talks OpenAI-format HTTP to the live container on :8601 (faster-whisper-small STT, Kokoro bm_george TTS with 24->16 kHz audioop resample); 'embedded' fallback kept behind the [speech] extra. Verified with a live TTS->STT round trip (warm: STT 0.27s, TTS 1.9s). Docker image is now slim (no CUDA/ML deps). Python pinned to 3.12 (system 3.8 too old, audioop gone in 3.13). - CI: .gitea/workflows/build.yml — lint+test on main pushes; on v* tags test, build gateway image, push to registry, release, and trigger Watchtower (tatlock pattern; needs REGISTRY_USER/REGISTRY_PASSWORD/ WATCHTOWER_TOKEN secrets). Runtime stack in deploy/desklock-gateway.yml. - architecture.md: measured speech latencies, deployed-Speaches status, CI & deployment section. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
62 lines
1.8 KiB
Python
62 lines
1.8 KiB
Python
"""Speech-to-text: Speaches over HTTP (default) or embedded faster-whisper.
|
|
|
|
The embedded import is deferred so the gateway runs without the heavy
|
|
[speech] extras installed.
|
|
"""
|
|
|
|
import io
|
|
import wave
|
|
|
|
import httpx
|
|
|
|
from .config import settings
|
|
|
|
_client: httpx.Client | None = None
|
|
_embedded_model = None
|
|
|
|
|
|
def transcribe(pcm: bytes, sample_rate: int) -> str:
|
|
"""Transcribe raw s16le mono PCM to text."""
|
|
if settings.stt_backend == "speaches":
|
|
return _transcribe_speaches(pcm, sample_rate)
|
|
return _transcribe_embedded(pcm)
|
|
|
|
|
|
def _wav_bytes(pcm: bytes, sample_rate: int) -> bytes:
|
|
buf = io.BytesIO()
|
|
with wave.open(buf, "wb") as w:
|
|
w.setnchannels(1)
|
|
w.setsampwidth(2)
|
|
w.setframerate(sample_rate)
|
|
w.writeframes(pcm)
|
|
return buf.getvalue()
|
|
|
|
|
|
def _transcribe_speaches(pcm: bytes, sample_rate: int) -> str:
|
|
global _client
|
|
if _client is None:
|
|
_client = httpx.Client(base_url=settings.speaches_base_url, timeout=60.0)
|
|
response = _client.post(
|
|
"/v1/audio/transcriptions",
|
|
files={"file": ("utterance.wav", _wav_bytes(pcm, sample_rate), "audio/wav")},
|
|
data={"model": settings.stt_model, "language": "en"},
|
|
)
|
|
response.raise_for_status()
|
|
return response.json()["text"].strip()
|
|
|
|
|
|
def _transcribe_embedded(pcm: bytes) -> str:
|
|
global _embedded_model
|
|
if _embedded_model is None:
|
|
from faster_whisper import WhisperModel
|
|
|
|
_embedded_model = WhisperModel(
|
|
settings.embedded_stt_model, device=settings.embedded_stt_device
|
|
)
|
|
|
|
import numpy as np
|
|
|
|
audio = np.frombuffer(pcm, dtype=np.int16).astype(np.float32) / 32768.0
|
|
segments, _info = _embedded_model.transcribe(audio, language="en")
|
|
return " ".join(segment.text.strip() for segment in segments).strip()
|