mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-08 09:32:20 +00:00
Code Issues Packages Projects Releases Wiki Activity
icefall/egs/aishell/ASR
History
Wei Kang ba257efbcd
Add Context biasing (#1038) 
* Add context biasing for librispeech

* Add context biasing for wenetspeech

* fix bugs

* Implement Aho-Corasick context graph

* fix some bugs

* Fixes to forward_one_step; add draw to context graph

* add output arc; fix black

* Fix wenetspeech tokenizer

* Minor fixes to the decode.py
2023-06-03 21:28:49 +08:00
..
conformer_ctc
manual correction of black formatting
2022-11-17 14:18:05 -05:00
conformer_mmi
apply black on all files
2022-11-17 09:42:17 -05:00
local
Training with byte level BPE (AIShell) (#986)
2023-05-04 19:16:17 +08:00
pruned_transducer_stateless2
Fix style issues. (#937)
2023-03-08 22:56:04 +08:00
pruned_transducer_stateless3
Shallow fusion for Aishell (#954)
2023-04-03 16:20:29 +08:00
pruned_transducer_stateless7
Add Context biasing (#1038)
2023-06-03 21:28:49 +08:00
pruned_transducer_stateless7_bbpe
Remove cur_batch_idx (#1102)
2023-05-30 14:49:54 +08:00
tdnn_lstm_ctc
Training with byte level BPE (AIShell) (#986)
2023-05-04 19:16:17 +08:00
transducer_stateless
Fix style issues. (#937)
2023-03-08 22:56:04 +08:00
transducer_stateless_modified
Fix style issues. (#937)
2023-03-08 22:56:04 +08:00
transducer_stateless_modified-2
Aishell pruned_transducer_stateless7 (#962)
2023-05-23 11:04:33 +08:00
prepare_aidatatang_200zh.sh
Use jsonl for CutSet in the LibriSpeech recipe. (#397)
2022-06-06 10:19:16 +08:00
prepare.sh
Training with byte level BPE (AIShell) (#986)
2023-05-04 19:16:17 +08:00
README.md
Aishell pruned_transducer_stateless7 (#962)
2023-05-23 11:04:33 +08:00
RESULTS.md
Aishell pruned_transducer_stateless7 (#962)
2023-05-23 11:04:33 +08:00
shared
Add aishell recipe (#30)
2021-11-18 10:00:47 +08:00

README.md

Introduction

Please refer to https://icefall.readthedocs.io/en/latest/recipes/Non-streaming-ASR/aishell/index.html for how to run models in this recipe.

Transducers

There are various folders containing the name transducer in this folder. The following table lists the differences among them.

Encoder Decoder Comment
transducer_stateless Conformer Embedding + Conv1d with k2.rnnt_loss
transducer_stateless_modified Conformer Embedding + Conv1d with modified transducer from optimized_transducer
transducer_stateless_modified-2 Conformer Embedding + Conv1d with modified transducer from optimized_transducer + extra data
pruned_transducer_stateless3 Conformer (reworked) Embedding + Conv1d pruned RNN-T + reworked model with random combiner + using aidatatang_20zh as extra data
pruned_transducer_stateless7 Zipformer Embedding pruned RNN-T + zipformer encoder + stateless decoder with context-size 1

The decoder in transducer_stateless is modified from the paper Rnn-Transducer with Stateless Prediction Network. We place an additional Conv1d layer right after the input embedding layer.