Downloads · 30 days
0
WayneWiser/icefall-asr-librispeech-conformer-ctc2-jit-bpe-500-2022-07-21
icefall-asr-librispeech-conformer-ctc2-jit-bpe-500-2022-07-21 is a machine learning model from WayneWiser. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model is a reworked CTC attention model trained with the code from github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/conformerctc2. The model has 12 layers of reworked Conformer encoder layers and 6 rewor…
Downloads · 30 days
0
Access
Public
Updated Dec 12, 2022
Repo size
2.6 GB
Likes
0
Public
Click a slice to open those files.
.pt2.5 GB · 97%
From the Hugging Face model README
This model is a reworked CTC attention model trained with the code from github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/conformer_ctc2. The model has 12 layers of reworked Conformer encoder layers and 6 reworked Transformer decoder layers. Number of model parameters is 103,071,035. With full Librispeech data set, it was trained for only 30 epochs because the reworked model would converge much faster.
For detailed information, please refer to https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/RESULTS.md or https://github.com/k2-fsa/icefall/pull/462.
For data/lang_bpe_500 and data/lm etc., please refer to https://huggingface.co/csukuangfj/icefall-asr-librispeech-conformer-ctc-jit-bpe-500-2021-11-09/