mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-19 05:54:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

update README.md

Browse Source
This commit is contained in:
yaozengwei 2022-06-13 13:42:12 +08:00
parent a1cbe1fd9c
commit de1fe9dac4
2 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
egs/librispeech/ASR/README.md
View File

@ -23,6 +23,7 @@ The following table lists the differences among them.
| `pruned_transducer_stateless5` | Conformer(modified) | Embedding + Conv1d | same as pruned_transducer_stateless4 + more layers + random combiner| | `pruned_transducer_stateless5` | Conformer(modified) | Embedding + Conv1d | same as pruned_transducer_stateless4 + more layers + random combiner|
| `pruned_transducer_stateless6` | Conformer(modified) | Embedding + Conv1d | same as pruned_transducer_stateless4 + distillation with hubert| | `pruned_transducer_stateless6` | Conformer(modified) | Embedding + Conv1d | same as pruned_transducer_stateless4 + distillation with hubert|
| `pruned_stateless_emformer_rnnt2` | Emformer(from torchaudio) | Embedding + Conv1d | Using Emformer from torchaudio for streaming ASR| | `pruned_stateless_emformer_rnnt2` | Emformer(from torchaudio) | Embedding + Conv1d | Using Emformer from torchaudio for streaming ASR|
| `conv_emformer_transducer_stateless` | Emformer | Embedding + Conv1d | Using Emformer augmented with convolution for streaming ASR + mechanisms in reworked model |
The decoder in `transducer_stateless` is modified from the paper The decoder in `transducer_stateless` is modified from the paper

4
egs/librispeech/ASR/conv_emformer_transducer_stateless/test_emformer.py
View File

@ -19,12 +19,10 @@
import torch import torch
from emformer import Emformer, stack_states, unstack_states from emformer import ConvolutionModule, Emformer, stack_states, unstack_states
def test_convolution_module_forward(): def test_convolution_module_forward():
from emformer import ConvolutionModule
B, D = 2, 256 B, D = 2, 256
chunk_length = 4 chunk_length = 4
right_context_length = 2 right_context_length = 2