Refactor code structure for improved readability and maintainability

workers/voice-to-text/Dockerfile

@@ -0,0 +1,20 @@
+# RunPod Serverless worker: Speech-to-Text (faster-whisper).
+# Lightweight — no torch/NeMo; ctranslate2 uses the CUDA + cuDNN in the base image.
+# Paths are relative to the REPO ROOT (RunPod's build context).
+FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        python3 python3-pip ffmpeg && \
+    ln -sf /usr/bin/python3 /usr/bin/python && \
+    rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+COPY workers/voice-to-text/requirements.txt .
+RUN pip3 install --no-cache-dir -r requirements.txt
+COPY workers/voice-to-text/handler.py .
+
+CMD ["python3", "-u", "handler.py"]

workers/voice-to-text/README.md

@@ -0,0 +1,48 @@
+# Speech-to-Text worker — Whisper (RunPod Serverless)
+
+Multilingual voice-to-text via **faster-whisper** — lets a worker **speak**
+instead of typing annotation text, in both the image and video editors. 99
+languages incl. Hindi/regional + English. Chosen over Parakeet/NeMo because it
+has no heavy dependencies (no NeMo, no torch), so it builds cleanly.
+
+## Contract
+
+Request → `POST /runsync`:
+```json
+{ "input": { "audio": "<base64 audio>", "language": "en", "timestamps": false } }
+```
+- `audio`: base64 wav/mp3/m4a (any sample rate — resampled internally)
+- `language`: optional (e.g. `"hi"`, `"en"`); omit to auto-detect
+- `timestamps`: optional — per-segment start/end
+
+Response → `{ "output": { "transcript": "...", "language": "en" } }`
+(with `segments: [{text, start_sec, end_sec}]` if `timestamps: true`), or `{ "output": { "error": "..." } }`.
+
+## Deploy (new endpoint — one per model)
+
+1. **RunPod → Serverless → New Endpoint → Deploy from a GitHub repository** → `Sumit-Pluto/photo_gallery`.
+2. **Dockerfile path:** `/workers/voice-to-text/Dockerfile`
+3. Config:
+   - **GPU:** light — **16 GB (T4 / A4000)** is plenty (`large-v3` ≈ 5 GB VRAM).
+   - **Network volume:** attach your weights volume (caches the model).
+   - **Workers:** Max 1, Active 0, FlashBoot on. **Execution timeout** ~300s (first-run download).
+4. **Warm up once** (downloads the model, ~1.5 GB):
+   ```bash
+   curl -X POST https://api.runpod.ai/v2/<NEW_ID>/runsync \
+     -H "Content-Type: application/json" -H "Authorization: Bearer <API_KEY>" \
+     -d '{"input":{"audio":"<base64-wav>","language":"en"}}'
+   ```
+5. In **Vercel**, set `RUNPOD_STT_URL` = `https://api.runpod.ai/v2/<NEW_ID>/runsync` (server-only).
+
+## Tuning (env vars)
+
+| Var | Default | Purpose |
+|---|---|---|
+| `WHISPER_MODEL` | `large-v3` | accuracy vs speed — `medium` / `small` are faster/lighter |
+| `WHISPER_COMPUTE` | `float16` | `int8_float16` uses less VRAM |
+
+## App integration (next step, not yet built)
+
+Mic-record button in the editor's text/annotation tool → `/api/ai/transcribe`
+(proxies here) → inserts the transcript. Client `rpTranscribe()` already exists in
+`apps/web/src/lib/runpod/endpoints.ts`.

workers/voice-to-text/handler.py

@@ -0,0 +1,91 @@
+"""
+RunPod Serverless worker: Speech-to-Text (Whisper via faster-whisper).
+
+Chosen over Parakeet/NeMo because it has NO heavy dependencies (no NeMo, no
+torch — just ctranslate2), so it builds cleanly, AND it's multilingual (99
+languages incl. Hindi/regional + English) — a better fit for a mixed crew.
+
+Lets a worker speak instead of typing annotation text (image + video editors).
+
+Matches the app's transcribe contract:
+  {"input": {
+     "audio": "<base64 audio>",   # required (wav/mp3/m4a; any sample rate — resampled internally)
+     "language": "en",            # optional (e.g. "hi", "en"); omit = auto-detect
+     "timestamps": false          # optional — return per-segment start/end
+  }}
+Returns: {"transcript": "...", "language": "en", "segments"?: [{text,start_sec,end_sec}]}
+         (or {"error": "..."}).
+
+Tuning (env): WHISPER_MODEL (default large-v3; "medium"/"small" are faster),
+WHISPER_COMPUTE (default float16; "int8_float16" for less VRAM).
+"""
+
+import base64
+import os
+import tempfile
+
+_VOLUME = "/runpod-volume"
+if os.path.isdir(_VOLUME):
+    os.environ.setdefault("HF_HOME", os.path.join(_VOLUME, "huggingface"))
+
+import runpod  # noqa: E402
+from faster_whisper import WhisperModel  # noqa: E402
+
+MODEL_SIZE = os.environ.get("WHISPER_MODEL", "large-v3")
+DEVICE = os.environ.get("WHISPER_DEVICE", "cuda")
+COMPUTE = os.environ.get("WHISPER_COMPUTE", "float16")
+
+_model = None
+
+
+def _get_model():
+    global _model
+    if _model is None:
+        _model = WhisperModel(
+            MODEL_SIZE,
+            device=DEVICE,
+            compute_type=COMPUTE,
+            download_root=os.environ.get("HF_HOME"),
+        )
+    return _model
+
+
+def handler(event):
+    inp = (event or {}).get("input") or {}
+    audio_b64 = inp.get("audio")
+    if not audio_b64:
+        return {"error": "Missing 'audio' (base64)."}
+
+    language = inp.get("language") or None
+    want_ts = bool(inp.get("timestamps", False))
+
+    path = None
+    try:
+        data = audio_b64.split(",", 1)[1] if "," in audio_b64 else audio_b64
+        with tempfile.NamedTemporaryFile(suffix=".audio", delete=False) as f:
+            f.write(base64.b64decode(data))
+            path = f.name
+
+        segments, info = _get_model().transcribe(path, language=language, vad_filter=True)
+
+        parts = []
+        segs = []
+        for s in segments:
+            parts.append(s.text)
+            if want_ts:
+                segs.append(
+                    {"text": s.text.strip(), "start_sec": round(s.start, 2), "end_sec": round(s.end, 2)}
+                )
+
+        out = {"transcript": "".join(parts).strip(), "language": info.language}
+        if want_ts:
+            out["segments"] = segs
+        return out
+    except Exception as exc:
+        return {"error": f"{type(exc).__name__}: {exc}"}
+    finally:
+        if path and os.path.exists(path):
+            os.unlink(path)
+
+
+runpod.serverless.start({"handler": handler})

workers/voice-to-text/requirements.txt

@@ -0,0 +1,2 @@
+runpod==1.7.9
+faster-whisper==1.0.3