137 lines
3.8 KiB
Go
137 lines
3.8 KiB
Go
package captions
|
|||
|
|
|
||
|
|
import (
|
||
|
|
"testing"
|
||
|
|
"time"
|
||
|
|
|
||
|
|
"tea.chunkbyte.com/kato/captioneer/src/audio"
|
||
|
|
"tea.chunkbyte.com/kato/captioneer/src/config"
|
||
|
|
)
|
||
|
|
|
||
|
|
type fakeSegment struct {
|
||
|
|
start int
|
||
|
|
samples []float32
|
||
|
|
}
|
||
|
|
|
||
|
|
type fakeTranscriber struct {
|
||
|
|
text string
|
||
|
|
decodeTexts []string
|
||
|
|
segments []fakeSegment
|
||
|
|
flushed bool
|
||
|
|
}
|
||
|
|
|
||
|
|
func (f *fakeTranscriber) Decode([]float32) string {
|
||
|
|
if len(f.decodeTexts) == 0 {
|
||
|
|
return f.text
|
||
|
|
}
|
||
|
|
text := f.decodeTexts[0]
|
||
|
|
f.decodeTexts = f.decodeTexts[1:]
|
||
|
|
return text
|
||
|
|
}
|
||
|
|
func (f *fakeTranscriber) AcceptVAD([]float32) {}
|
||
|
|
func (f *fakeTranscriber) FlushVAD() { f.flushed = true }
|
||
|
|
func (f *fakeTranscriber) NextSpeechSegment() (int, []float32, bool) {
|
||
|
|
if len(f.segments) == 0 {
|
||
|
|
return 0, nil, false
|
||
|
|
}
|
||
|
|
segment := f.segments[0]
|
||
|
|
f.segments = f.segments[1:]
|
||
|
|
return segment.start, segment.samples, true
|
||
|
|
}
|
||
|
|
|
||
|
|
func TestFixedModeEmitsFinalCaption(t *testing.T) {
|
||
|
|
transcriber := &fakeTranscriber{text: "hello"}
|
||
|
|
var events []Event
|
||
|
|
processor := New(config.Settings{Mode: config.ModeFixed, ChunkDuration: time.Second}, transcriber, func(event Event) error {
|
||
|
|
events = append(events, event)
|
||
|
|
return nil
|
||
|
|
})
|
||
|
|
|
||
|
|
if err := processor.Accept(make([]float32, audio.SampleRate)); err != nil {
|
||
|
|
t.Fatal(err)
|
||
|
|
}
|
||
|
|
if len(events) != 1 || events[0].Kind != Final || events[0].Text != "hello" {
|
||
|
|
t.Fatalf("unexpected events: %#v", events)
|
||
|
|
}
|
||
|
|
if events[0].StartedAt != 0 || events[0].EndedAt != time.Second {
|
||
|
|
t.Fatalf("unexpected timestamps: %#v", events[0])
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
func TestFixedModeFlushesFinalPartialChunkWithExactTimestamps(t *testing.T) {
|
||
|
|
transcriber := &fakeTranscriber{decodeTexts: []string{"first", "partial"}}
|
||
|
|
var events []Event
|
||
|
|
processor := New(config.Settings{Mode: config.ModeFixed, ChunkDuration: time.Second}, transcriber, func(event Event) error {
|
||
|
|
events = append(events, event)
|
||
|
|
return nil
|
||
|
|
})
|
||
|
|
|
||
|
|
if err := processor.Accept(make([]float32, audio.SampleRate+audio.SampleRate/2)); err != nil {
|
||
|
|
t.Fatal(err)
|
||
|
|
}
|
||
|
|
if err := processor.Flush(); err != nil {
|
||
|
|
t.Fatal(err)
|
||
|
|
}
|
||
|
|
if len(events) != 2 {
|
||
|
|
t.Fatalf("event count = %d, want 2", len(events))
|
||
|
|
}
|
||
|
|
if events[1].Text != "partial" || events[1].StartedAt != time.Second || events[1].EndedAt != 1500*time.Millisecond {
|
||
|
|
t.Fatalf("unexpected partial event: %#v", events[1])
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
func TestVADModeEmitsProvisionalThenFinal(t *testing.T) {
|
||
|
|
transcriber := &fakeTranscriber{text: "speech"}
|
||
|
|
var events []Event
|
||
|
|
processor := New(config.Settings{
|
||
|
|
Mode: config.ModeVAD,
|
||
|
|
ChunkDuration: time.Second,
|
||
|
|
PreviewThresholdDB: -45,
|
||
|
|
}, transcriber, func(event Event) error {
|
||
|
|
events = append(events, event)
|
||
|
|
return nil
|
||
|
|
})
|
||
|
|
|
||
|
|
loud := make([]float32, audio.SampleRate)
|
||
|
|
for i := range loud {
|
||
|
|
loud[i] = 0.5
|
||
|
|
}
|
||
|
|
if err := processor.Accept(loud); err != nil {
|
||
|
|
t.Fatal(err)
|
||
|
|
}
|
||
|
|
transcriber.segments = []fakeSegment{{start: 0, samples: loud}}
|
||
|
|
if err := processor.Accept(make([]float32, audio.SamplesPerPacket())); err != nil {
|
||
|
|
t.Fatal(err)
|
||
|
|
}
|
||
|
|
|
||
|
|
if len(events) != 2 || events[0].Kind != Provisional || events[1].Kind != Final {
|
||
|
|
t.Fatalf("unexpected events: %#v", events)
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
func TestEmptyFinalEmitsHide(t *testing.T) {
|
||
|
|
transcriber := &fakeTranscriber{text: " \n\t "}
|
||
|
|
var event Event
|
||
|
|
processor := New(config.Settings{Mode: config.ModeFixed, ChunkDuration: time.Second}, transcriber, func(got Event) error {
|
||
|
|
event = got
|
||
|
|
return nil
|
||
|
|
})
|
||
|
|
if err := processor.Accept(make([]float32, audio.SampleRate)); err != nil {
|
||
|
|
t.Fatal(err)
|
||
|
|
}
|
||
|
|
if event.Kind != Hide {
|
||
|
|
t.Fatalf("event kind = %d, want Hide", event.Kind)
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
func TestFlushFlushesVAD(t *testing.T) {
|
||
|
|
transcriber := &fakeTranscriber{}
|
||
|
|
processor := New(config.Settings{Mode: config.ModeVAD, ChunkDuration: time.Second}, transcriber, func(Event) error { return nil })
|
||
|
|
if err := processor.Flush(); err != nil {
|
||
|
|
t.Fatal(err)
|
||
|
|
}
|
||
|
|
if !transcriber.flushed {
|
||
|
|
t.Fatal("VAD was not flushed")
|
||
|
|
}
|
||
|
|
}
|