Added support for a minimal JSON output schema
This commit is contained in:
@@ -216,6 +216,7 @@ seriatim merge \
|
||||
--preprocessing-modules validate-raw,normalize-speakers,trim-text \
|
||||
--postprocessing-modules detect-overlaps,resolve-overlaps,backchannel,filler,coalesce,detect-overlaps,autocorrect,assign-ids,validate-output \
|
||||
--output-modules json \
|
||||
--output-schema seriatim \
|
||||
--output-file merged.json \
|
||||
--report-file report.json
|
||||
```
|
||||
@@ -260,7 +261,7 @@ type Postprocessor interface {
|
||||
|
||||
type OutputWriter interface {
|
||||
Name() string
|
||||
Write(ctx context.Context, out FinalTranscript, report Report, cfg Config) ([]ReportEvent, error)
|
||||
Write(ctx context.Context, out any, report Report, cfg Config) ([]ReportEvent, error)
|
||||
}
|
||||
```
|
||||
|
||||
@@ -386,7 +387,7 @@ A valid merged transcript should satisfy:
|
||||
- Any `overlap_group_id` on a segment refers to an existing overlap group.
|
||||
- Every overlap group references at least two segments.
|
||||
- Every referenced segment exists.
|
||||
- Output validates against the output schema.
|
||||
- Output validates against the selected output schema.
|
||||
|
||||
## Determinism Requirements
|
||||
|
||||
|
||||
Reference in New Issue
Block a user