-
There should be a functionality where instead of having to download entire dataset and train on it, we could download just partial data and use only that for training. And if not, then the documentati…
-
I am trying to understand the requirements on the RNNLM for LODR rescoring
I am using something along the lines of Librispeech pruned_transducer_stateless3 recipe with
https://github.com/k2-fsa/ic…
-
Appreciate for the job on supporting RNN-T training on CPU (models/language_modeling/pytorch/rnnt/training/cpu), just quick evaluated the training code and found that WER would keep in 1.00 after even…
-
Hi, thanks for your work.
The training code is for CTC model ,did you get the rnn-t result (greedy | 20.74) by jsut swiching imported Transducer model with all other hyparameters the same???
-
Hi!
I am currently working on a streaming Transformer Transducer (T-T) myself (using Tensorflow) but I'm struggling to get started with the actual inference part. I've been referred to your reposit…
-
Traceback (most recent call last):
File "/home/pika-main/trainer/train_transducer_bmuf_otfaug.py", line 305, in
model.cuda(args.local_rank)
File "/root/anaconda3/lib/python3.6/site-package…
-
I am getting a lot of deletions in my RNN-T training/decoding setup relative to Transformer/Conformer. The data is the "Malach" corpus; about 200 hours of English but accented speech from Holocaust su…
-
hello
I would like to ask you a question that may be somewhat trivial.
The shape of logits of RNN T loss is Batch, max_seq_len, max_target_len+1, class.
Why is max_target_len+1 here?
Shouldn't t…
-
I am looking at the beam search decoding script for RNN-T models in espnet1 https://github.com/espnet/espnet/blob/c4aba12f9de93cb021e869a2ecce61da18b0c484/espnet/nets/beam_search_transducer.py#L247. I…
-
Hi,
In icefall, there are multiple decoding methods available, eg. greedy_search, beam_search, modified_beam_search, fast_beam_search, fast_beam_search_nbest. There are some other decoding methods …