selfhostyourtech/reflector
2
0
Fork 0
mirror of https://github.com/Monadical-SAS/reflector.git synced 2026-03-21 22:56:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: enable daily co in selfhosted + only schedule tasks when necessary (#883)

Browse Source 
* feat: enable daily co in selfhosted + only schedule tasks when necessary

* feat: refactor aws storage to be platform agnostic + add local pad tracking with slfhosted support
This commit is contained in:
Juan Diego García
2026-03-02 11:08:20 -05:00
committed by GitHub
parent f6cc03286b
commit 045eae8ff2
23 changed files with 1442 additions and 165 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gpu/self_hosted/app/factory.py
View File

@@ -3,6 +3,7 @@ from contextlib import asynccontextmanager
from fastapi import FastAPI
from .routers.diarization import router as diarization_router
from .routers.padding import router as padding_router
from .routers.transcription import router as transcription_router
from .routers.translation import router as translation_router
from .services.transcriber import WhisperService
@@ -27,4 +28,5 @@ def create_app() -> FastAPI:
app.include_router(transcription_router)
app.include_router(translation_router)
app.include_router(diarization_router)
app.include_router(padding_router)
return app

199
gpu/self_hosted/app/routers/padding.py Normal file
View File

@@ -0,0 +1,199 @@
"""
Audio padding endpoint for selfhosted GPU service.
CPU-intensive audio padding service for adding silence to audio tracks.
Uses PyAV filter graph (adelay) for precise track synchronization.
IMPORTANT: This padding logic is duplicated from server/reflector/utils/audio_padding.py
for deployment isolation (self_hosted can't import from server/reflector/). If you modify
the PyAV filter graph or padding algorithm, you MUST update both:
- gpu/self_hosted/app/routers/padding.py (this file)
- server/reflector/utils/audio_padding.py
Constants duplicated from server/reflector/utils/audio_constants.py for same reason.
"""
import logging
import math
import os
import tempfile
from fractions import Fraction
import av
import requests
from av.audio.resampler import AudioResampler
from fastapi import APIRouter, Depends, HTTPException
from pydantic import BaseModel
from ..auth import apikey_auth
logger = logging.getLogger(__name__)
router = APIRouter(tags=["padding"])
# ref B0F71CE8-FC59-4AA5-8414-DAFB836DB711
OPUS_STANDARD_SAMPLE_RATE = 48000
OPUS_DEFAULT_BIT_RATE = 128000
S3_TIMEOUT = 60
class PaddingRequest(BaseModel):
track_url: str
output_url: str
start_time_seconds: float
track_index: int
class PaddingResponse(BaseModel):
size: int
cancelled: bool = False
@router.post("/pad", dependencies=[Depends(apikey_auth)], response_model=PaddingResponse)
def pad_track(req: PaddingRequest):
"""Pad audio track with silence using PyAV adelay filter graph."""
if not req.track_url:
raise HTTPException(status_code=400, detail="track_url cannot be empty")
if not req.output_url:
raise HTTPException(status_code=400, detail="output_url cannot be empty")
if req.start_time_seconds <= 0:
raise HTTPException(
status_code=400,
detail=f"start_time_seconds must be positive, got {req.start_time_seconds}",
)
if req.start_time_seconds > 18000:
raise HTTPException(
status_code=400,
detail="start_time_seconds exceeds maximum 18000s (5 hours)",
)
logger.info(
"Padding request: track %d, delay=%.3fs", req.track_index, req.start_time_seconds
)
temp_dir = tempfile.mkdtemp()
input_path = None
output_path = None
try:
# Download source audio
logger.info("Downloading track for padding")
response = requests.get(req.track_url, stream=True, timeout=S3_TIMEOUT)
response.raise_for_status()
input_path = os.path.join(temp_dir, "track.webm")
total_bytes = 0
with open(input_path, "wb") as f:
for chunk in response.iter_content(chunk_size=8192):
if chunk:
f.write(chunk)
total_bytes += len(chunk)
logger.info("Track downloaded: %d bytes", total_bytes)
# Apply padding using PyAV
output_path = os.path.join(temp_dir, "padded.webm")
delay_ms = math.floor(req.start_time_seconds * 1000)
logger.info("Padding track %d with %dms delay using PyAV", req.track_index, delay_ms)
in_container = av.open(input_path)
in_stream = next((s for s in in_container.streams if s.type == "audio"), None)
if in_stream is None:
in_container.close()
raise HTTPException(status_code=400, detail="No audio stream in input")
with av.open(output_path, "w", format="webm") as out_container:
out_stream = out_container.add_stream("libopus", rate=OPUS_STANDARD_SAMPLE_RATE)
out_stream.bit_rate = OPUS_DEFAULT_BIT_RATE
graph = av.filter.Graph()
abuf_args = (
f"time_base=1/{OPUS_STANDARD_SAMPLE_RATE}:"
f"sample_rate={OPUS_STANDARD_SAMPLE_RATE}:"
f"sample_fmt=s16:"
f"channel_layout=stereo"
)
src = graph.add("abuffer", args=abuf_args, name="src")
aresample_f = graph.add("aresample", args="async=1", name="ares")
delays_arg = f"{delay_ms}|{delay_ms}"
adelay_f = graph.add(
"adelay", args=f"delays={delays_arg}:all=1", name="delay"
)
sink = graph.add("abuffersink", name="sink")
src.link_to(aresample_f)
aresample_f.link_to(adelay_f)
adelay_f.link_to(sink)
graph.configure()
resampler = AudioResampler(
format="s16", layout="stereo", rate=OPUS_STANDARD_SAMPLE_RATE
)
for frame in in_container.decode(in_stream):
out_frames = resampler.resample(frame) or []
for rframe in out_frames:
rframe.sample_rate = OPUS_STANDARD_SAMPLE_RATE
rframe.time_base = Fraction(1, OPUS_STANDARD_SAMPLE_RATE)
src.push(rframe)
while True:
try:
f_out = sink.pull()
except Exception:
break
f_out.sample_rate = OPUS_STANDARD_SAMPLE_RATE
f_out.time_base = Fraction(1, OPUS_STANDARD_SAMPLE_RATE)
for packet in out_stream.encode(f_out):
out_container.mux(packet)
# Flush filter graph
src.push(None)
while True:
try:
f_out = sink.pull()
except Exception:
break
f_out.sample_rate = OPUS_STANDARD_SAMPLE_RATE
f_out.time_base = Fraction(1, OPUS_STANDARD_SAMPLE_RATE)
for packet in out_stream.encode(f_out):
out_container.mux(packet)
# Flush encoder
for packet in out_stream.encode(None):
out_container.mux(packet)
in_container.close()
file_size = os.path.getsize(output_path)
logger.info("Padding complete: %d bytes", file_size)
# Upload padded track
logger.info("Uploading padded track to S3")
with open(output_path, "rb") as f:
upload_response = requests.put(req.output_url, data=f, timeout=S3_TIMEOUT)
upload_response.raise_for_status()
logger.info("Upload complete: %d bytes", file_size)
return PaddingResponse(size=file_size)
except HTTPException:
raise
except Exception as e:
logger.error("Padding failed for track %d: %s", req.track_index, e, exc_info=True)
raise HTTPException(status_code=500, detail=f"Padding failed: {e}") from e
finally:
if input_path and os.path.exists(input_path):
try:
os.unlink(input_path)
except Exception as e:
logger.warning("Failed to cleanup input file: %s", e)
if output_path and os.path.exists(output_path):
try:
os.unlink(output_path)
except Exception as e:
logger.warning("Failed to cleanup output file: %s", e)
try:
os.rmdir(temp_dir)
except Exception as e:
logger.warning("Failed to cleanup temp directory: %s", e)

1
gpu/self_hosted/pyproject.toml
View File

@@ -16,4 +16,5 @@ dependencies = [
"sentencepiece",
"pyannote.audio==3.1.0",
"torchaudio>=2.3.0",
"av>=13.1.0",
]

5
gpu/self_hosted/uv.lock generated
View File

@@ -726,7 +726,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/44/69/9b804adb5fd0671f367781560eb5eb586c4d495277c93bde4307b9e28068/greenlet-3.2.4-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:3b67ca49f54cede0186854a008109d6ee71f66bd57bb36abd6d0a0267b540cdd", size = 274079, upload-time = "2025-08-07T13:15:45.033Z" },
{ url = "https://files.pythonhosted.org/packages/46/e9/d2a80c99f19a153eff70bc451ab78615583b8dac0754cfb942223d2c1a0d/greenlet-3.2.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ddf9164e7a5b08e9d22511526865780a576f19ddd00d62f8a665949327fde8bb", size = 640997, upload-time = "2025-08-07T13:42:56.234Z" },
{ url = "https://files.pythonhosted.org/packages/3b/16/035dcfcc48715ccd345f3a93183267167cdd162ad123cd93067d86f27ce4/greenlet-3.2.4-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:f28588772bb5fb869a8eb331374ec06f24a83a9c25bfa1f38b6993afe9c1e968", size = 655185, upload-time = "2025-08-07T13:45:27.624Z" },
{ url = "https://files.pythonhosted.org/packages/31/da/0386695eef69ffae1ad726881571dfe28b41970173947e7c558d9998de0f/greenlet-3.2.4-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:5c9320971821a7cb77cfab8d956fa8e39cd07ca44b6070db358ceb7f8797c8c9", size = 649926, upload-time = "2025-08-07T13:53:15.251Z" },
{ url = "https://files.pythonhosted.org/packages/68/88/69bf19fd4dc19981928ceacbc5fd4bb6bc2215d53199e367832e98d1d8fe/greenlet-3.2.4-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:c60a6d84229b271d44b70fb6e5fa23781abb5d742af7b808ae3f6efd7c9c60f6", size = 651839, upload-time = "2025-08-07T13:18:30.281Z" },
{ url = "https://files.pythonhosted.org/packages/19/0d/6660d55f7373b2ff8152401a83e02084956da23ae58cddbfb0b330978fe9/greenlet-3.2.4-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3b3812d8d0c9579967815af437d96623f45c0f2ae5f04e366de62a12d83a8fb0", size = 607586, upload-time = "2025-08-07T13:18:28.544Z" },
{ url = "https://files.pythonhosted.org/packages/8e/1a/c953fdedd22d81ee4629afbb38d2f9d71e37d23caace44775a3a969147d4/greenlet-3.2.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:abbf57b5a870d30c4675928c37278493044d7c14378350b3aa5d484fa65575f0", size = 1123281, upload-time = "2025-08-07T13:42:39.858Z" },
@@ -737,7 +736,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/49/e8/58c7f85958bda41dafea50497cbd59738c5c43dbbea5ee83d651234398f4/greenlet-3.2.4-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:1a921e542453fe531144e91e1feedf12e07351b1cf6c9e8a3325ea600a715a31", size = 272814, upload-time = "2025-08-07T13:15:50.011Z" },
{ url = "https://files.pythonhosted.org/packages/62/dd/b9f59862e9e257a16e4e610480cfffd29e3fae018a68c2332090b53aac3d/greenlet-3.2.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cd3c8e693bff0fff6ba55f140bf390fa92c994083f838fece0f63be121334945", size = 641073, upload-time = "2025-08-07T13:42:57.23Z" },
{ url = "https://files.pythonhosted.org/packages/f7/0b/bc13f787394920b23073ca3b6c4a7a21396301ed75a655bcb47196b50e6e/greenlet-3.2.4-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:710638eb93b1fa52823aa91bf75326f9ecdfd5e0466f00789246a5280f4ba0fc", size = 655191, upload-time = "2025-08-07T13:45:29.752Z" },
{ url = "https://files.pythonhosted.org/packages/f2/d6/6adde57d1345a8d0f14d31e4ab9c23cfe8e2cd39c3baf7674b4b0338d266/greenlet-3.2.4-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:c5111ccdc9c88f423426df3fd1811bfc40ed66264d35aa373420a34377efc98a", size = 649516, upload-time = "2025-08-07T13:53:16.314Z" },
{ url = "https://files.pythonhosted.org/packages/7f/3b/3a3328a788d4a473889a2d403199932be55b1b0060f4ddd96ee7cdfcad10/greenlet-3.2.4-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d76383238584e9711e20ebe14db6c88ddcedc1829a9ad31a584389463b5aa504", size = 652169, upload-time = "2025-08-07T13:18:32.861Z" },
{ url = "https://files.pythonhosted.org/packages/ee/43/3cecdc0349359e1a527cbf2e3e28e5f8f06d3343aaf82ca13437a9aa290f/greenlet-3.2.4-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:23768528f2911bcd7e475210822ffb5254ed10d71f4028387e5a99b4c6699671", size = 610497, upload-time = "2025-08-07T13:18:31.636Z" },
{ url = "https://files.pythonhosted.org/packages/b8/19/06b6cf5d604e2c382a6f31cafafd6f33d5dea706f4db7bdab184bad2b21d/greenlet-3.2.4-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:00fadb3fedccc447f517ee0d3fd8fe49eae949e1cd0f6a611818f4f6fb7dc83b", size = 1121662, upload-time = "2025-08-07T13:42:41.117Z" },
@@ -748,7 +746,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/22/5c/85273fd7cc388285632b0498dbbab97596e04b154933dfe0f3e68156c68c/greenlet-3.2.4-cp314-cp314-macosx_11_0_universal2.whl", hash = "sha256:49a30d5fda2507ae77be16479bdb62a660fa51b1eb4928b524975b3bde77b3c0", size = 273586, upload-time = "2025-08-07T13:16:08.004Z" },
{ url = "https://files.pythonhosted.org/packages/d1/75/10aeeaa3da9332c2e761e4c50d4c3556c21113ee3f0afa2cf5769946f7a3/greenlet-3.2.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:299fd615cd8fc86267b47597123e3f43ad79c9d8a22bebdce535e53550763e2f", size = 686346, upload-time = "2025-08-07T13:42:59.944Z" },
{ url = "https://files.pythonhosted.org/packages/c0/aa/687d6b12ffb505a4447567d1f3abea23bd20e73a5bed63871178e0831b7a/greenlet-3.2.4-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:c17b6b34111ea72fc5a4e4beec9711d2226285f0386ea83477cbb97c30a3f3a5", size = 699218, upload-time = "2025-08-07T13:45:30.969Z" },
{ url = "https://files.pythonhosted.org/packages/dc/8b/29aae55436521f1d6f8ff4e12fb676f3400de7fcf27fccd1d4d17fd8fecd/greenlet-3.2.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:b4a1870c51720687af7fa3e7cda6d08d801dae660f75a76f3845b642b4da6ee1", size = 694659, upload-time = "2025-08-07T13:53:17.759Z" },
{ url = "https://files.pythonhosted.org/packages/92/2e/ea25914b1ebfde93b6fc4ff46d6864564fba59024e928bdc7de475affc25/greenlet-3.2.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:061dc4cf2c34852b052a8620d40f36324554bc192be474b9e9770e8c042fd735", size = 695355, upload-time = "2025-08-07T13:18:34.517Z" },
{ url = "https://files.pythonhosted.org/packages/72/60/fc56c62046ec17f6b0d3060564562c64c862948c9d4bc8aa807cf5bd74f4/greenlet-3.2.4-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:44358b9bf66c8576a9f57a590d5f5d6e72fa4228b763d0e43fee6d3b06d3a337", size = 657512, upload-time = "2025-08-07T13:18:33.969Z" },
{ url = "https://files.pythonhosted.org/packages/23/6e/74407aed965a4ab6ddd93a7ded3180b730d281c77b765788419484cdfeef/greenlet-3.2.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:2917bdf657f5859fbf3386b12d68ede4cf1f04c90c3a6bc1f013dd68a22e2269", size = 1612508, upload-time = "2025-11-04T12:42:23.427Z" },
@@ -2072,6 +2069,7 @@ name = "reflector-gpu"
version = "0.1.0"
source = { virtual = "." }
dependencies = [
{ name = "av" },
{ name = "fastapi", extra = ["standard"] },
{ name = "faster-whisper" },
{ name = "librosa" },
@@ -2087,6 +2085,7 @@ dependencies = [
[package.metadata]
requires-dist = [
{ name = "av", specifier = ">=13.1.0" },
{ name = "fastapi", extras = ["standard"], specifier = ">=0.116.1" },
{ name = "faster-whisper", specifier = ">=1.1.0" },
{ name = "librosa", specifier = "==0.10.1" },