Wilson Wongso

icon indicating a website link wilsonwongso.dev icon indicating an email [email protected]

icon company @bookbot-kids @bookbot-hive @lazarusnlp icon location Jakarta, Indonesia icon location Machine Learning Engineer. Natural & Speech Language Processing.

Results 5 issues of Wilson Wongso

Fine-tuning wav2vec 2.0 with `torch.compile`

3 comment

### System Info - `transformers` version: 4.28.1 - Platform: Linux-4.19.0-23-cloud-amd64-x86_64-with-glibc2.28 - Python version: 3.9.0 - Huggingface_hub version: 0.13.3 - Safetensors version: not installed - PyTorch version (GPU?): 2.0.0+cu117 (True) -...

CMU Dictionary IPA Train/Test Dataset

Thank you for this great work! I'm planning to train a phonemizer model of my own and wanted to compare the results to that of your `en_us_cmudict_ipa_forward` model. It would...

Zipformer CTC HLG Decode to Words

7 comment

Hi. I have a phoneme-based Zipformer model, and I have successfully integrated a HLG component which takes the phonemes and converts it to a sequence of words. I've tried the...

High duration loss

15 comment

Hi @p0p4k, thanks for making this repo! I am currently trying to train a 44.1kHz English model, but my model is struggling with a rather high duration loss when compared...

Hotwords encoding for phonemes

8 comment

Hi. I have a phoneme-based Zipformer model. Before this [PR](https://github.com/k2-fsa/sherpa-onnx/pull/828), I was able to apply hotwords encoding for phoneme sequences, e.g. `ɪ z/dʒ ʌ s t/b ɛ s t`, following...