ThangLD201

@wq2012 Could you help me ?

> I do have the same problem with Vietnamese w2v2 asr model and a 3-gram LM model. I solved the problem by passing a known  word list (unigram) and prune...

@lopez86 Could you help me ?

@yixinL7 I also found that the 'article' field and the 'abstract' field in the preprocessed data is misaligned (I checked around ~10, all of which were mismatched), and besides being...

@msaroufim Could you help me ?

@msaroufim Thank you for the explanation. I'm trying to deploy Huggingface Wav2Vec2 models for serving with TorchServe, but haven't found a way to do this as there are no related...

The model receives float tensors as inputs and output logits, which are then decoded to human-readable text. Since TorchServe provides supports for Huggingface language models, which also receive tensors as...

@msaroufim The ```sample``` above is a dict, and may look like this. But for inference we only need the ```['audio']['array']``` property. ``` {'accent': 'us', 'age': 'fourties', 'audio': {'array': array([0. ,...

@chcg Are there any updates on this ? I also want to use nppftp with Proxy, but haven't figured how to ..