Document WhisperX transcribe integration

This commit is contained in:
2026-05-03 15:45:56 -05:00
parent 2438a0b7a5
commit 4a85da66e7
5 changed files with 45 additions and 23 deletions

View File

@@ -2,7 +2,7 @@
`narratio` is a Go-based orchestration application for processing D&D session audio into transcripts and downstream artifacts.
This repository currently contains a **working scaffold** with strict config loading, local workdir/manifest handling, resumable stage control, and placeholder adapters/stages.
This repository currently contains a **working scaffold** with strict config loading, local workdir/manifest handling, resumable stage control, a real WhisperX HTTP adapter, and a real `prepare` + `transcribe` path.
## Expected Config Files
@@ -25,18 +25,17 @@ Example minimal files are available under `examples/`:
## Current Scaffold Status
Implemented in scaffold form:
Implemented now:
- strict config load + validation
- local artifact/workdir creation and locking
- manifest create/load/save and stage status tracking
- stage framework with real `prepare` stage and placeholder downstream stages
- stage framework with real `prepare` and `transcribe` stages; placeholder downstream stages
- resumable run control (`run`, `resume`, `run-stage`, `plan` with run/skip decisions)
- fake/no-op adapters for external tool boundaries
- real WhisperX HTTP adapter plus fake/no-op adapters for test/scaffold usage
Not implemented yet:
- real WhisperX HTTP integration
- real Seriatim execution
- real Audita execution
- real analyzer integration
@@ -55,9 +54,11 @@ go test ./...
go run ./cmd/narratio plan --config examples/pipeline.minimal.yml --session examples/session.minimal.yml
```
## Run Placeholder Pipeline
## Run Pipeline (Current State)
The current `run` command executes available scaffold behavior (`prepare` + placeholder stages) and records progress in `manifest.json`.
The current `run` command executes `prepare` + real `transcribe` + placeholder downstream stages and records progress in `manifest.json`.
Note: default CLI wiring currently injects `whisperx.NoopClient` in the runner to avoid implicit network dependency; the real HTTP adapter is implemented under `internal/adapters/whisperx/http.go` and is used via explicit env wiring/tests.
```bash
go run ./cmd/narratio run --config examples/pipeline.minimal.yml --session examples/session.minimal.yml