use parakeet.cpp instead of whisper

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 +236,16 @@ models:
       --parallel 1
       ${common_args}
 
-  # STT via whisper.cpp (Vulkan GPU on RX 580, always loaded, ~600MB VRAM)
-  # Model auto-downloaded by init container, see deployment.yaml
-  # Note: Vulkan whisper on AMD GPUs has known quality issues on some cards;
-  # if transcriptions come out as garbage/gibberish, add --no-gpu to fall back.
-  "whisper-small":
+  # STT via parakeet-server (parakeet.cpp OpenAI-compatible server, CPU, always loaded)
+  # Model downloaded on first start and cached under /root/.cache/parakeet.cpp/models
+  # Exposes POST /v1/audio/transcriptions (OpenAI-compatible)
+  "parakeet-tdt_ctc-1.1b":
     checkEndpoint: none
     cmd: |
-      whisper-server
+      parakeet-server
         --port ${PORT}
-        -m /root/.cache/whisper/ggml-small.bin
-        --request-path /v1/audio
-        --inference-path /transcriptions
-        --convert
-        --threads 6
+        --model tdt_ctc-1.1b-q4_k.gguf
+        --cache-dir /root/.cache/parakeet.cpp/models
 
 
   # Image generation via stable-diffusion.cpp (sd-server)

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/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
@@ -92,7 +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)