mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-12-11 06:55:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

remove unwanted changes

Browse Source
This commit is contained in:
Desh Raj 2023-06-13 08:02:40 -04:00
parent 0cad336277
commit 8623a1bcb2
1 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
egs/librispeech/ASR/README.md
View File

@ -26,7 +26,6 @@ The following table lists the differences among them.
| `pruned_transducer_stateless7_ctc` | Zipformer | Embedding + Conv1d | Same as pruned_transducer_stateless7, but with extra CTC head|
| `pruned_transducer_stateless7_ctc_bs` | Zipformer | Embedding + Conv1d | pruned_transducer_stateless7_ctc + blank skip |
| `pruned_transducer_stateless7_streaming` | Streaming Zipformer | Embedding + Conv1d | streaming version of pruned_transducer_stateless7 |
| `pruned_transducer_stateless7_streaming_multi` | Streaming Zipformer | Embedding + Conv1d | same as pruned_transducer_stateless7_streaming, trained on LibriSpeech + GigaSpeech |
| `pruned_transducer_stateless8` | Zipformer | Embedding + Conv1d | Same as pruned_transducer_stateless7, but using extra data from GigaSpeech|
| `pruned_stateless_emformer_rnnt2` | Emformer(from torchaudio) | Embedding + Conv1d | Using Emformer from torchaudio for streaming ASR|
| `conv_emformer_transducer_stateless` | ConvEmformer | Embedding + Conv1d | Using ConvEmformer for streaming ASR + mechanisms in reworked model |
@ -34,7 +33,6 @@ The following table lists the differences among them.
| `lstm_transducer_stateless` | LSTM | Embedding + Conv1d | Using LSTM with mechanisms in reworked model |
| `lstm_transducer_stateless2` | LSTM | Embedding + Conv1d | Using LSTM with mechanisms in reworked model + gigaspeech (multi-dataset setup) |
| `lstm_transducer_stateless3` | LSTM | Embedding + Conv1d | Using LSTM with mechanisms in reworked model + gradient filter + delay penalty |
| `zipformer` | Upgraded Zipformer | Embedding + Conv1d | The latest recipe |
The decoder in `transducer_stateless` is modified from the paper
[Rnn-Transducer with Stateless Prediction Network](https://ieeexplore.ieee.org/document/9054419/).
@ -47,7 +45,6 @@ We place an additional Conv1d layer right after the input embedding layer.
| `conformer-ctc` | Conformer | Use auxiliary attention head |
| `conformer-ctc2` | Reworked Conformer | Use auxiliary attention head |
| `conformer-ctc3` | Reworked Conformer | Streaming version + delay penalty |
| `zipformer-ctc` | Zipformer | Use auxiliary attention head |
# MMI