Update renovate/renovate Docker tag to v43.220.0

.woodpecker/renovate.yaml

@@ -21,7 +21,7 @@ steps:
       - bao kv get -mount secret -field RENOVATE_TOKEN renovate > /woodpecker/renovate_token
       - bao kv get -mount secret -field GITHUB_COM_TOKEN renovate > /woodpecker/github_com_token
   - name: Run Renovate
-    image: renovate/renovate:43.217.1
+    image: renovate/renovate:43.220.0
     environment:
       RENOVATE_AUTODISCOVER: "true"
       RENOVATE_ENDPOINT: https://gitea.lumpiasty.xyz/api/v1

apps/llama/configs/config.yaml

@@ -19,7 +19,7 @@ hooks:
   on_startup:
     preload:
       - "Qwen3.5-0.8B-GGUF-nothink:Q4_K_XL"
-      - "whisper-small"
+      - "parakeet-tdt_ctc-1.1b"
 
 # matrix replaces groups (they are mutually exclusive).
 # The small 0.8B model runs alongside any LLM.
@@ -27,7 +27,7 @@ hooks:
 matrix:
   vars:
     q8: "Qwen3.5-0.8B-GGUF-nothink:Q4_K_XL"
-    stt: "whisper-small"
+    stt: "parakeet-tdt_ctc-1.1b"
     flux: "flux2-klein-4b:Q4_K_M"
     coder: "Qwen3-Coder-Next-GGUF:Q4_K_M"
     q35t: "Qwen3.5-35B-A3B-GGUF:Q4_K_M"
@@ -58,6 +58,7 @@ matrix:
     # FLUX runs alone — evicts everything including q8, but keeps STT for voice during image gen
     image_gen: "flux & stt"
 
+
 models:
   "Qwen3-Coder-Next-GGUF:Q4_K_M":
     cmd: |
@@ -235,20 +236,14 @@ models:
       --parallel 1
       ${common_args}
 
-  # STT via whisper.cpp (Vulkan GPU on RX 580, always loaded, ~600MB VRAM)
+  # STT via parakeet-server (parakeet.cpp OpenAI-compatible server, CPU, always loaded)
-  # Model auto-downloaded by init container, see deployment.yaml
+  # Model downloaded on first start and cached under /root/.cache/parakeet.cpp/models
-  # Note: Vulkan whisper on AMD GPUs has known quality issues on some cards;
+  # parakeet-proxy.py sits in front to convert any audio format to WAV via ffmpeg,
-  # if transcriptions come out as garbage/gibberish, add --no-gpu to fall back.
+  # since parakeet-server only accepts real WAV but browsers send Ogg/Opus.
-  "whisper-small":
+  "parakeet-tdt_ctc-1.1b":
     checkEndpoint: none
     cmd: |
-      whisper-server
+      env PROXY_PORT=${PORT} FFMPEG_BIN=/root/.cache/ffmpeg/ffmpeg python3 /config/parakeet-proxy.py
-        --port ${PORT}
-        -m /root/.cache/whisper/ggml-small.bin
-        --request-path /v1/audio
-        --inference-path /transcriptions
-        --convert
-        --threads 6
 
 
   # Image generation via stable-diffusion.cpp (sd-server)

apps/llama/configs/parakeet-proxy.py

@@ -0,0 +1,227 @@
+#!/usr/bin/env python3
+"""
+Thin reverse proxy for parakeet-server.
+
+Accepts POST /v1/audio/transcriptions with any audio format,
+converts the audio to 16 kHz mono WAV via ffmpeg, then forwards
+the converted file to the real parakeet-server running on PARAKEET_PORT.
+
+Also proxies GET /health straight through.
+
+Usage:
+    PROXY_PORT=<port>  PARAKEET_PORT=<upstream>  python3 parakeet-proxy.py
+"""
+
+import http.server
+import io
+import os
+import subprocess
+import sys
+import tempfile
+import urllib.request
+import urllib.error
+
+PROXY_PORT    = int(os.environ.get("PROXY_PORT", "8080"))
+PARAKEET_PORT = PROXY_PORT + 1
+FFMPEG        = os.environ.get("FFMPEG_BIN", "ffmpeg")
+MODEL         = os.environ.get("PARAKEET_MODEL", "tdt_ctc-1.1b-q4_k.gguf")
+CACHE_DIR     = os.environ.get("PARAKEET_CACHE_DIR", "/root/.cache/parakeet.cpp/models")
+
+
+def convert_to_wav(data: bytes) -> bytes:
+    """Convert any audio bytes to 16 kHz mono PCM WAV via ffmpeg."""
+    with tempfile.NamedTemporaryFile(suffix=".input", delete=False) as inf:
+        inf.write(data)
+        inf_path = inf.name
+    out_path = inf_path + ".wav"
+    try:
+        subprocess.run(
+            [
+                FFMPEG, "-y",
+                "-i", inf_path,
+                "-ar", "16000",
+                "-ac", "1",
+                "-f", "wav",
+                out_path,
+            ],
+            check=True,
+            stdout=subprocess.DEVNULL,
+            stderr=subprocess.DEVNULL,
+        )
+        with open(out_path, "rb") as f:
+            return f.read()
+    finally:
+        os.unlink(inf_path)
+        if os.path.exists(out_path):
+            os.unlink(out_path)
+
+
+def parse_multipart(content_type: str, body: bytes):
+    """
+    Parse a multipart/form-data body.
+    Returns a dict of field_name -> (filename_or_None, content_type, data).
+    """
+    import email
+    from email import policy as email_policy
+
+    # email.parser needs the full MIME headers to parse multipart
+    raw = b"Content-Type: " + content_type.encode() + b"\r\n\r\n" + body
+    msg = email.message_from_bytes(raw, policy=email_policy.compat32)
+    parts = {}
+    for part in msg.get_payload():
+        cd = part.get("Content-Disposition", "")
+        name = None
+        filename = None
+        for item in cd.split(";"):
+            item = item.strip()
+            if item.startswith('name='):
+                name = item[5:].strip('"')
+            elif item.startswith('filename='):
+                filename = item[9:].strip('"')
+        if name is not None:
+            parts[name] = (filename, part.get_content_type(), part.get_payload(decode=True))
+    return parts
+
+
+def build_multipart(fields: dict) -> tuple[bytes, str]:
+    """
+    Build a multipart/form-data body from fields dict:
+      field_name -> (filename_or_None, content_type, data_bytes)
+    Returns (body_bytes, content_type_header_value).
+    """
+    boundary = b"----ParakeetProxyBoundary0xDEADBEEF"
+    body = b""
+    for name, (filename, ct, data) in fields.items():
+        body += b"--" + boundary + b"\r\n"
+        if filename:
+            body += (
+                f'Content-Disposition: form-data; name="{name}"; filename="{filename}"\r\n'
+            ).encode()
+        else:
+            body += f'Content-Disposition: form-data; name="{name}"\r\n'.encode()
+        body += f"Content-Type: {ct}\r\n\r\n".encode()
+        body += data + b"\r\n"
+    body += b"--" + boundary + b"--\r\n"
+    return body, f"multipart/form-data; boundary={boundary.decode()}"
+
+
+class ProxyHandler(http.server.BaseHTTPRequestHandler):
+    def log_message(self, fmt, *args):
+        print(f"[parakeet-proxy] {self.address_string()} - {fmt % args}", flush=True)
+
+    def do_GET(self):
+        if self.path == "/health":
+            self._forward_get("/health")
+        else:
+            self.send_response(404)
+            self.end_headers()
+
+    def do_POST(self):
+        if self.path.rstrip("/") == "/v1/audio/transcriptions":
+            self._handle_transcription()
+        else:
+            self.send_response(404)
+            self.end_headers()
+
+    def _forward_get(self, path):
+        try:
+            url = f"http://127.0.0.1:{PARAKEET_PORT}{path}"
+            with urllib.request.urlopen(url, timeout=5) as resp:
+                body = resp.read()
+                self.send_response(resp.status)
+                self.send_header("Content-Type", resp.headers.get("Content-Type", "application/json"))
+                self.end_headers()
+                self.wfile.write(body)
+        except Exception as e:
+            self.send_response(502)
+            self.end_headers()
+            self.wfile.write(str(e).encode())
+
+    def _handle_transcription(self):
+        length = int(self.headers.get("Content-Length", 0))
+        body = self.rfile.read(length)
+        ct = self.headers.get("Content-Type", "")
+
+        try:
+            fields = parse_multipart(ct, body)
+        except Exception as e:
+            self._error(400, f"failed to parse multipart: {e}")
+            return
+
+        if "file" not in fields:
+            self._error(400, "missing required field 'file'")
+            return
+
+        filename, file_ct, audio_data = fields["file"]
+
+        # Convert to WAV regardless of what we received
+        try:
+            wav_data = convert_to_wav(audio_data)
+        except subprocess.CalledProcessError:
+            self._error(400, "ffmpeg could not decode audio")
+            return
+        except Exception as e:
+            self._error(500, f"conversion error: {e}")
+            return
+
+        # Rebuild multipart with converted WAV, preserve other fields
+        new_fields = {}
+        for name, (fn, fct, data) in fields.items():
+            if name == "file":
+                new_fields[name] = ("recording.wav", "audio/wav", wav_data)
+            else:
+                new_fields[name] = (fn, fct, data)
+
+        new_body, new_ct = build_multipart(new_fields)
+
+        # Forward to parakeet-server
+        try:
+            url = f"http://127.0.0.1:{PARAKEET_PORT}/v1/audio/transcriptions"
+            req = urllib.request.Request(
+                url,
+                data=new_body,
+                headers={"Content-Type": new_ct},
+                method="POST",
+            )
+            with urllib.request.urlopen(req, timeout=300) as resp:
+                resp_body = resp.read()
+                self.send_response(resp.status)
+                self.send_header("Content-Type", resp.headers.get("Content-Type", "application/json"))
+                self.end_headers()
+                self.wfile.write(resp_body)
+        except urllib.error.HTTPError as e:
+            resp_body = e.read()
+            self.send_response(e.code)
+            self.send_header("Content-Type", e.headers.get("Content-Type", "application/json"))
+            self.end_headers()
+            self.wfile.write(resp_body)
+        except Exception as e:
+            self._error(502, f"upstream error: {e}")
+
+    def _error(self, code: int, msg: str):
+        body = f'{{"error":{{"message":"{msg}","type":"proxy_error"}}}}'.encode()
+        self.send_response(code)
+        self.send_header("Content-Type", "application/json")
+        self.end_headers()
+        self.wfile.write(body)
+
+
+if __name__ == "__main__":
+    proc = subprocess.Popen([
+        "parakeet-server",
+        "--host", "127.0.0.1",
+        "--port", str(PARAKEET_PORT),
+        "--model", MODEL,
+        "--cache-dir", CACHE_DIR,
+    ])
+    print(f"[parakeet-proxy] started parakeet-server pid={proc.pid} on :{PARAKEET_PORT}", flush=True)
+
+    server = http.server.HTTPServer(("0.0.0.0", PROXY_PORT), ProxyHandler)
+    print(f"[parakeet-proxy] listening on :{PROXY_PORT}", flush=True)
+    try:
+        server.serve_forever()
+    except KeyboardInterrupt:
+        pass
+    finally:
+        proc.terminate()
+        proc.wait()

apps/llama/deployment.yaml

@@ -18,7 +18,7 @@ spec:
     spec:
       initContainers:
         - name: download-whisper
-          image: ghcr.io/mostlygeek/llama-swap:unified-vulkan-2026-06-09
+          image: gitea.lumpiasty.xyz/lumpiasty/llama-swap:unified-vulkan-parakeet-2026-06-09
           command:
             - sh
             - -c
@@ -48,7 +48,7 @@ spec:
               mountPath: /root/.cache
       containers:
         - name: llama-swap
-          image: ghcr.io/mostlygeek/llama-swap:unified-vulkan-2026-06-09
+          image: gitea.lumpiasty.xyz/lumpiasty/llama-swap:unified-vulkan-parakeet-2026-06-09
           imagePullPolicy: IfNotPresent
           command:
             - llama-swap

apps/llama/kustomization.yaml

@@ -13,3 +13,4 @@ configMapGenerator:
     namespace: llama
     files:
       - config.yaml=configs/config.yaml
+      - parakeet-proxy.py=configs/parakeet-proxy.py

apps/openwebui/release.yaml

@@ -84,7 +84,7 @@ spec:
         value: "Users"
       - name: OAUTH_AUTO_REDIRECT
         value: "true"
-      # STT via whisper-server (routed through llama-swap)
+      # STT via parakeet-server (routed through llama-swap)
       - name: AUDIO_STT_ENGINE
         value: "openai"
       - name: AUDIO_STT_OPENAI_API_BASE_URL
@@ -92,9 +92,7 @@ spec:
       - name: AUDIO_STT_OPENAI_API_KEY
         value: "ignored"
       - name: AUDIO_STT_MODEL
-        value: "whisper-small"
+        value: "parakeet-tdt_ctc-1.1b"
-      - name: AUDIO_STT_SUPPORTED_CONTENT_TYPES
-        value: "audio/wav,audio/wave"
       # TTS via OuteTTS (routed through llama-swap)
       # TTS via dedicated Kokoro server (CPU-only, separate pod)
       - name: AUDIO_TTS_ENGINE