1035 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Fangjun Kuang	0b656e4e1c	Add a link to Colab. (#14) ... It demonstrates the usages of pre-trained models.	2021-08-20 15:43:25 +08:00
Fangjun Kuang	9d0cc9d829	Support computing nbest oracle WER. (#10) ... * Support computing nbest oracle WER. * Add scale to all nbest based decoding/rescoring methods. * Add script to run pretrained models. * Use torchaudio to extract features. * Support decoding multiple files at the same time. Also, use kaldifeat for feature extraction. * Support decoding with LM rescoring and attention-decoder rescoring. * Minor fixes. * Replace scale with lattice-score-scale. * Add usage example with a provided pretrained model.	2021-08-20 11:53:37 +08:00
pkufool	ef233486ae	The training script produce WER of 2.57% on librispeech test-clean (#13) ... * Add grad_clip and weight-decay, small fix of dataloader and masking * Add RESULTS.md	2021-08-20 10:08:08 +08:00
Fangjun Kuang	caa0b9e942	Fix an error in displaying decoding process. (#12)	2021-08-19 14:54:01 +08:00
Fangjun Kuang	1c3b13c7eb	Minor fixes. (#9)	2021-08-16 19:01:25 +08:00
Fangjun Kuang	12a2fd023e	Add doc about installation and usage (#7) ... * Add readme. * Add TOC. * fix typos * Minor fixes after review.	2021-08-12 12:44:04 +08:00
Fangjun Kuang	5a0b9bcb23	Refactoring (#4) ... * Fix an error in TDNN-LSTM training. * WIP: Refactoring * Refactor transformer.py * Remove unused code. * Minor fixes.	2021-08-04 14:53:02 +08:00
Daniel Povey	cf8d76293d	Merge pull request #3 from csukuangfj/style-check ... Add CTC training	2021-07-31 15:36:00 +08:00
Fangjun Kuang	398ed80d7a	Minor fixes to support DDP training.	2021-07-31 15:26:57 +08:00
Fangjun Kuang	b94d97da37	Disable gradient computation in evaluation mode.	2021-07-29 20:37:31 +08:00
Fangjun Kuang	acc63a9172	WIP: Add BPE training code.	2021-07-29 20:23:52 +08:00
Fangjun Kuang	bd69e4be32	Use attention decoder for rescoring.	2021-07-28 12:22:09 +08:00
Fangjun Kuang	f65854cca5	Add BPE decoding results.	2021-07-27 17:38:47 +08:00
Fangjun Kuang	4ccae509d3	WIP: Begin to add BPE decoding	2021-07-26 20:06:58 +08:00
Fangjun Kuang	d3101fb005	Fix loading checkpoint in DDP training.	2021-07-26 08:08:14 +08:00
Fangjun Kuang	78bb65ed78	Fix an error in DDP training.	2021-07-25 22:33:09 +08:00
Fangjun Kuang	8055bf31a0	Support DDP training.	2021-07-25 21:40:09 +08:00
Fangjun Kuang	4a66712406	Add LM rescoring.	2021-07-25 18:21:26 +08:00
Fangjun Kuang	6f9fe5b906	Refactor decoding code.	2021-07-24 22:23:50 +08:00
Fangjun Kuang	00f8371f37	begin to add LM rescoring.	2021-07-24 18:24:04 +08:00
Fangjun Kuang	a9095925ba	Fix CI test errors.	2021-07-24 18:13:03 +08:00
Fangjun Kuang	54436182a4	Fix CI.	2021-07-24 18:05:19 +08:00
Fangjun Kuang	ee83a3e67c	Fix CI dependencies installation.	2021-07-24 17:55:45 +08:00
Fangjun Kuang	2e33e24348	Add CI test.	2021-07-24 17:47:41 +08:00
Fangjun Kuang	f3542c7793	Add CTC training.	2021-07-24 17:13:20 +08:00
Fangjun Kuang	a01d08f73c	Add self-loops to propagate disambiguation symbols.	2021-07-21 13:12:20 +08:00
Fangjun Kuang	8a72901f3a	Minor fixes.	2021-07-20 19:54:12 +08:00
Fangjun Kuang	d5e0408698	Add prepare_lang.py based on prepare_lang.sh	2021-07-20 19:41:21 +08:00
Fangjun Kuang	e005ea062c	Minor fixes after review.	2021-07-20 10:02:20 +08:00
Fangjun Kuang	f25eedf2d4	Fixes after review.	2021-07-20 00:14:24 +08:00
Fangjun Kuang	0b19aa09c1	Compute features of librispeech and musan.	2021-07-19 23:35:32 +08:00
Fangjun Kuang	40eed74460	Download LM for LibriSpeech.	2021-07-15 21:09:14 +08:00
Fangjun Kuang	d146a4e799	Remove mypy.	2021-07-15 19:52:01 +08:00
Fangjun Kuang	71c4e29ad5	Add style check tools.	2021-07-15 17:36:48 +08:00
Fangjun Kuang	0d16431766	First commit.	2021-07-15 17:35:54 +08:00