Keysat
95524f4983
After five hotfix iterations on the WhisperX install (v0.12.0:0–:4) we
never got a working docker build. The fundamental constraint isn't
patchable from outside NVIDIA: NGC PyTorch on ARM64 (the only base that
runs on Spark 2's GB10 Blackwell) ships a custom-versioned torch
2.10.0a0+b558c98 that has no pre-built torchaudio match anywhere.
WhisperX → pyannote → torchaudio is a hard dependency chain we couldn't
satisfy without rebuilding torchaudio against torch 2.10's alpha API.
Walking away cleanly is better than another night of chasing.
Removed from the codebase:
- image/whisperx_container/* (Dockerfile + requirements + app/main.py)
- image/app/whisperx_install.py (install manager + SSH ship-context logic)
- image/Dockerfile COPY whisperx_container
- WHISPERX_* config keys in config.py
- whisperx service entry in services.py
- WhisperX-preferred branch in audio_proxy.py
- /api/whisperx/* endpoints in server.py
- install banner + progress dialog in index.html
- render + handlers in app.js
- .whisperx-install styles in style.css
Spark 2 cleaned in tandem (user-authorized): container removed,
~/whisperx-build/ removed, 5.4 GB of dangling image layers + 1.3 GB of
builder cache reclaimed. parakeet-asr and magpie-tts unaffected and
healthy throughout.
The audio path is back to exactly what shipped in v0.11.0:3:
POST /api/audio/transcribe-with-speakers
→ Parakeet (transcription) + Sortformer (diarization) in parallel
→ merged by timestamp into speaker-labeled blocks
v0.13.0:1+ will add the actually-needed fixes that the WhisperX detour
was meant to address:
1. memory cap on the parakeet-asr container so a long-audio crash
can't swap-thrash Spark 2 again
2. a chunking proxy in /api/audio/transcribe-with-speakers that
splits inputs >10 min before Sortformer
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
78 lines
2.5 KiB
Python
78 lines
2.5 KiB
Python
from __future__ import annotations
|
|
import os
|
|
from dataclasses import dataclass
|
|
from pathlib import Path
|
|
|
|
|
|
def _env(name: str, default: str = "") -> str:
|
|
return os.environ.get(name, default)
|
|
|
|
|
|
def _resolve_models_yaml() -> str:
|
|
if env := os.environ.get("MODELS_YAML"):
|
|
return env
|
|
here = Path(__file__).resolve().parent # app/
|
|
candidates = [
|
|
here.parent / "models.yaml", # image/models.yaml (Docker)
|
|
here.parent.parent / "models.yaml", # <repo>/models.yaml (dev)
|
|
Path("/app/models.yaml"), # explicit container path
|
|
]
|
|
for p in candidates:
|
|
if p.exists():
|
|
return str(p)
|
|
return str(candidates[0]) # let load fail with a clear path
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class Settings:
|
|
spark1_host: str
|
|
spark1_user: str
|
|
spark2_host: str
|
|
spark2_user: str
|
|
parakeet_host: str
|
|
parakeet_user: str
|
|
parakeet_container: str
|
|
magpie_host: str
|
|
magpie_user: str
|
|
magpie_container: str
|
|
ssh_key_path: str
|
|
ssh_known_hosts: str
|
|
models_yaml: str
|
|
vllm_port: int
|
|
parakeet_port: int
|
|
magpie_port: int
|
|
bind_port: int
|
|
open_webui_url: str
|
|
ngc_api_key: str
|
|
|
|
@classmethod
|
|
def from_env(cls) -> "Settings":
|
|
spark2_host = _env("SPARK2_HOST")
|
|
spark2_user = _env("SPARK2_USER")
|
|
# Parakeet and Magpie default to Spark 2 unless explicitly overridden.
|
|
return cls(
|
|
spark1_host=_env("SPARK1_HOST"),
|
|
spark1_user=_env("SPARK1_USER"),
|
|
spark2_host=spark2_host,
|
|
spark2_user=spark2_user,
|
|
parakeet_host=_env("PARAKEET_HOST") or spark2_host,
|
|
parakeet_user=_env("PARAKEET_USER") or spark2_user,
|
|
parakeet_container=_env("PARAKEET_CONTAINER") or "parakeet-asr",
|
|
magpie_host=_env("MAGPIE_HOST") or spark2_host,
|
|
magpie_user=_env("MAGPIE_USER") or spark2_user,
|
|
magpie_container=_env("MAGPIE_CONTAINER") or "magpie-tts",
|
|
ssh_key_path=_env("SSH_KEY_PATH"),
|
|
ssh_known_hosts=_env("SSH_KNOWN_HOSTS"),
|
|
models_yaml=_resolve_models_yaml(),
|
|
vllm_port=int(_env("VLLM_PORT", "8888")),
|
|
parakeet_port=int(_env("PARAKEET_PORT", "8000")),
|
|
magpie_port=int(_env("MAGPIE_PORT", "9000")),
|
|
bind_port=int(_env("BIND_PORT", "9999")),
|
|
open_webui_url=_env("OPEN_WEBUI_URL", ""),
|
|
ngc_api_key=_env("NGC_API_KEY", ""),
|
|
)
|
|
|
|
@property
|
|
def configured(self) -> bool:
|
|
return bool(self.spark1_host)
|