Word-level timestamp? Translation?

[jtkeyva]

Great to see this in an easy to use ready to go package!

Is it possible to output word-level timestamps etc like in the examples? How about translating? Thanks

./main -m ./models/ggml-base.en.bin -f ./samples/jfk.wav -ml 1

whisper_model_load: loading model from './models/ggml-base.en.bin'
...
system_info: n_threads = 4 / 10 | AVX2 = 0 | AVX512 = 0 | NEON = 1 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 |

main: processing './samples/jfk.wav' (176000 samples, 11.0 sec), 4 threads, 1 processors, lang = en, task = transcribe, timestamps = 1 ...

[00:00:00.000 --> 00:00:00.320]
[00:00:00.320 --> 00:00:00.370]   And
[00:00:00.370 --> 00:00:00.690]   so
[00:00:00.690 --> 00:00:00.850]   my
[00:00:00.850 --> 00:00:01.590]   fellow
[00:00:01.590 --> 00:00:02.850]   Americans
[00:00:02.850 --> 00:00:03.300]  ,
[00:00:03.300 --> 00:00:04.140]   ask
[00:00:04.140 --> 00:00:04.990]   not
[00:00:04.990 --> 00:00:05.410]   what
[00:00:05.410 --> 00:00:05.660]   your
[00:00:05.660 --> 00:00:06.260]   country
[00:00:06.260 --> 00:00:06.600]   can
[00:00:06.600 --> 00:00:06.840]   do
[00:00:06.840 --> 00:00:07.010]   for
[00:00:07.010 --> 00:00:08.170]   you
[00:00:08.170 --> 00:00:08.190]  ,
[00:00:08.190 --> 00:00:08.430]   ask
[00:00:08.430 --> 00:00:08.910]   what
[00:00:08.910 --> 00:00:09.040]   you
[00:00:09.040 --> 00:00:09.320]   can
[00:00:09.320 --> 00:00:09.440]   do
[00:00:09.440 --> 00:00:09.760]   for
[00:00:09.760 --> 00:00:10.020]   your
[00:00:10.020 --> 00:00:10.510]   country
[00:00:10.510 --> 00:00:11.000]  .

-tr,       --translate         [false  ] translate from source language to english

[krikristoophe]

Hello, Thanks for you proposals !

For the timestamps I will look at the possibilities when I have available time !

For the translation there is a parameter but I didn't test it for the moment

[krikristoophe]

https://github.com/krikristoophe/whisper_flutter_plus/issues/2

[krikristoophe]

https://github.com/krikristoophe/whisper_flutter_plus/issues/3

[krikristoophe]

@jtkeyva I published a new version with both of your proposals. You can use version 1.0.0 and use it like the README.md exemple :

Quickstart

// Prepare wav file
final Directory documentDirectory = await getApplicationDocumentsDirectory();
final ByteData documentBytes = await rootBundle.load('assets/jfk.wav');

final String jfkPath = '${documentDirectory.path}/jfk.wav';

await File(jfkPath).writeAsBytes(
    documentBytes.buffer.asUint8List(),
);

// Begin whisper transcription
final Whisper whisper = Whisper(
    model: WhisperModel.base,
);

final String? whisperVersion = await whisper.getVersion();
print(whisperVersion);

final String transcription = await whisper.transcribe(
    transcribeRequest: TranscribeRequest(
        audio: jfkPath,
        isTranslate: true, // Translate result from audio lang to english text
        isNoTimestamps: false, // Get segments in result
        splitOnWord: true, // Split segments on each word 
    ),
);
print(transcription);

[jtkeyva]

@krikristoophe awesome thank you very much!!