feat(aquamarine): serve Whisper transcription from the NPU (#472)

The goal is speech recognition on the NPU for vinput, and sherpa-onnx cannot
deliver it: every model it loads keeps a dynamic time axis, which the NPU
compiler rejects outright. Qwen3-ASR and SenseVoice both core-dumped in
vpux-compiler ("Got non broadcastable dimensions pair"), and reshaping the ONNX
inputs does not help because the dynamic dimensions sit inside the graph
(WA-037). Whisper is the only family OpenVINO publishes fully static IRs for,
and its fixed 30 s window is exactly what the compiler accepts.

The host now runs an OpenAI-compatible /v1/audio/transcriptions service backed
by whisper-large-v3-turbo int8 on the NPU: 1.5 s for 11 s of audio against
2.1 s on CPU, with the compiled graph cached in /var/cache so only a cold cache
pays the ~60 s NPU compile. vinput on the desktop sends raw PCM to it through a
small provider script.

Only the NPU driver and compiler still come from the unmerged branch in the
`nixpkgs-npu` input (NixOS/nixpkgs#570230), whose nixpkgs also happens to be
the one where openvino-genai 2026.4.0.0 builds at all.

Assisted-by: DeepSeek Harness 0.2.1-rc.2 (deepseek-v4.1-flash)

home/linux/gui/base/vinput/aqua-provider.py

@@ -0,0 +1,78 @@
+"""vinput ASR provider: send recorded PCM to the aquamarine Whisper service.
+
+vinput pipes raw PCM (S16_LE, mono, 16 kHz) to stdin and reads the transcript
+from stdout. The service speaks the OpenAI transcription API, so the PCM is
+wrapped in a WAV container and POSTed as multipart.
+"""
+
+import io
+import json
+import os
+import sys
+import uuid
+import wave
+from urllib.error import URLError
+from urllib.request import Request, urlopen
+
+URL = os.environ["VINPUT_ASR_URL"]
+TIMEOUT = float(os.environ.get("VINPUT_ASR_TIMEOUT", "60"))
+SAMPLE_RATE = 16000
+FILE_FIELD = (
+    'Content-Disposition: form-data; name="file"; filename="audio.wav"'
+)
+
+
+def as_wav(pcm: bytes) -> bytes:
+    buffer = io.BytesIO()
+    with wave.open(buffer, "wb") as wav:
+        wav.setnchannels(1)
+        wav.setsampwidth(2)
+        wav.setframerate(SAMPLE_RATE)
+        wav.writeframes(pcm)
+    return buffer.getvalue()
+
+
+def multipart(wav: bytes) -> tuple[bytes, str]:
+    boundary = f"----vinput{uuid.uuid4().hex}"
+    body = bytearray()
+    body += f"--{boundary}\r\n".encode()
+    body += FILE_FIELD.encode() + b"\r\n"
+    body += b"Content-Type: audio/wav\r\n\r\n"
+    body += wav
+    body += b"\r\n"
+    body += f"--{boundary}\r\n".encode()
+    body += b'Content-Disposition: form-data; name="model"\r\n\r\n'
+    body += b"whisper-large-v3-turbo\r\n"
+    language = os.environ.get("VINPUT_ASR_LANGUAGE", "")
+    if language:
+        body += f"--{boundary}\r\n".encode()
+        body += b'Content-Disposition: form-data; name="language"\r\n\r\n'
+        body += f"{language}\r\n".encode()
+    body += f"--{boundary}--\r\n".encode()
+    return bytes(body), f"multipart/form-data; boundary={boundary}"
+
+
+def main() -> int:
+    pcm = sys.stdin.buffer.read()
+    if not pcm:
+        print("no audio on stdin", file=sys.stderr)
+        return 1
+    payload, content_type = multipart(as_wav(pcm))
+    request = Request(
+        URL,
+        data=payload,
+        headers={"Content-Type": content_type},
+        method="POST",
+    )
+    try:
+        with urlopen(request, timeout=TIMEOUT) as response:
+            transcript = json.load(response)
+    except (URLError, OSError, ValueError) as exc:
+        print(f"transcription request failed: {exc}", file=sys.stderr)
+        return 1
+    print(transcript.get("text", "").strip())
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

home/linux/gui/base/vinput/config.json

@@ -13,7 +13,7 @@
         "duck_output_volume": 0.25
     },
     "asr": {
-        "active_provider": "sherpa-onnx",
+        "active_provider": "aqua-whisper",
         "normalize_audio": true,
         "input_gain": 1.0,
         "vad": {
@@ -29,6 +29,15 @@
                 "type": "local",
                 "model": "model.sherpa-onnx.qwen3-asr-0.6b-int8",
                 "timeout_ms": 15000
+            },
+            {
+                "id": "aqua-whisper",
+                "type": "command",
+                "command": "/home/ryan/.config/vinput/aqua-asr-provider",
+                "env": {
+                    "VINPUT_ASR_URL": "http://192.168.5.101:18080/v1/audio/transcriptions"
+                },
+                "timeout_ms": 60000
             }
         ]
     },

home/linux/gui/base/vinput/default.nix

@@ -38,6 +38,12 @@ in
       force = true;
     };
 
+    # The OpenAI-transcription client vinput runs as a provider. config.json points at this
+    # absolute path, so the two must stay in sync.
+    xdg.configFile."vinput/aqua-asr-provider".source =
+      pkgs.writers.writePython3 "vinput-aqua-asr-provider" { }
+        ./aqua-provider.py;
+
     systemd.user.services.vinput-daemon = {
       Unit = {
         Description = "Fcitx5 Vinput voice input daemon";