Emmanuel Schmidbauer comments

Results 48 comments of


                                            Emmanuel Schmidbauer

wasm-ld: error: duplicate symbol

![image](https://github.com/rhasspy/piper-phonemize/assets/7139998/f5900c54-92e7-44e8-86f6-bc1e80ceeb9c) building on an m2

Add Whisper Voice Activity Detector (VAD) or Silero VAD for silence suppression

also looking to use silerovad v5 onnx in transformers.js - wonder if someone could share a working example

save speech separation results to disk throw IndexError，size of diarization.labels() and shape of sources.data is not same

i am also running into this issue using the following code: ```python for s, speaker in enumerate(diarization.labels()): audio = np.float32(sources.data[:, s] / np.max(np.abs(sources.data[:, s]))) # noqa ```

pretrained model (`enc_dec_fix_phonemes.pt`) for testing inference

sure - if you could share here, that would be great!

Use Silero VAD in Batched Mode

im also experiencing this issue- seems like an urgent fix. Can we get it merged?

Flutter (Dart) apps fail Apple's submission validation, likely due to libsherpa dylib being present in root of Frameworks folder

any update on this? i'm trying to build for iOS and encountering same error. here are some steps i outlined based on the resources in this thread: ```bash bash build-ios-shared.sh...

Absolute speaker diarization?

could you share you implemented VAD?

ModuleNotFoundError: No module named 'openvoice.text'

encountering the same issue