mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-08 17:42:21 +00:00
Code Issues Packages Projects Releases Wiki Activity
icefall/egs/librispeech/ASR
History
Fangjun Kuang ac84220de9
Modified conformer with multi datasets (#312) 
* Copy files for editing.

* Use librispeech + gigaspeech with modified conformer.

* Support specifying number of workers for on-the-fly feature extraction.

* Feature extraction code for GigaSpeech.

* Combine XL splits lazily during training.

* Fix warnings in decoding.

* Add decoding code for GigaSpeech.

* Fix decoding the gigaspeech dataset.

We have to use the decoder/joiner networks for the GigaSpeech dataset.

* Disable speed perturbe for XL subset.

* Compute the Nbest oracle WER for RNN-T decoding.

* Minor fixes.

* Minor fixes.

* Add results.

* Update results.

* Update CI.

* Update results.

* Fix style issues.

* Update results.

* Fix style issues.
2022-04-29 15:40:30 +08:00
..
conformer_ctc
Fix potential bugs in PyTorch that exist in label_smoothing. (#300)
2022-04-08 13:41:33 +08:00
conformer_mmi
Change for asr_datamodule.py (#241)
2022-03-14 00:30:58 +08:00
local
Modified conformer with multi datasets (#312)
2022-04-29 15:40:30 +08:00
pruned_transducer_stateless
Modified conformer with multi datasets (#312)
2022-04-29 15:40:30 +08:00
pruned_transducer_stateless2
Modified conformer with multi datasets (#312)
2022-04-29 15:40:30 +08:00
pruned_transducer_stateless3
Modified conformer with multi datasets (#312)
2022-04-29 15:40:30 +08:00
streaming_conformer_ctc
Reset seed at the beginning of each epoch. (#221)
2022-02-21 15:16:39 +08:00
tdnn_lstm_ctc
Some cleanups
2022-04-04 13:37:10 +08:00
transducer
Fix some typos. (#329)
2022-04-22 15:54:59 +08:00
transducer_lstm
Fix some typos. (#329)
2022-04-22 15:54:59 +08:00
transducer_stateless
Support computing RNN-T loss with torchaudio (#316)
2022-04-19 18:47:13 +08:00
transducer_stateless2
Support computing RNN-T loss with torchaudio (#316)
2022-04-19 18:47:13 +08:00
transducer_stateless_multi_datasets
Don't use a lambda for dataloader's worker_init_fn. (#284)
2022-03-31 20:32:00 +08:00
.gitignore
Modified conformer with multi datasets (#312)
2022-04-29 15:40:30 +08:00
prepare_giga_speech.sh
Modified conformer with multi datasets (#312)
2022-04-29 15:40:30 +08:00
prepare.sh
Add LG decoding (#277)
2022-04-19 17:23:46 +08:00
README.md
Modified conformer with multi datasets (#312)
2022-04-29 15:40:30 +08:00
RESULTS-100hours.md
Update result for full libri + GigaSpeech using transducer_stateless. (#231)
2022-03-01 17:01:46 +08:00
RESULTS.md
Modified conformer with multi datasets (#312)
2022-04-29 15:40:30 +08:00
shared
Refactoring (#4)
2021-08-04 14:53:02 +08:00

README.md

Introduction Please refer to https://icefall.readthedocs.io/en/latest/recipes/librispeech/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 Conformer LSTM
transducer_stateless Conformer Embedding + Conv1d Using optimized_transducer from computing RNN-T loss
transducer_stateless2 Conformer Embedding + Conv1d Using torchaudio for computing RNN-T loss
transducer_lstm LSTM LSTM
transducer_stateless_multi_datasets Conformer Embedding + Conv1d Using data from GigaSpeech as extra training data
pruned_transducer_stateless Conformer Embedding + Conv1d Using k2 pruned RNN-T loss
pruned_transducer_stateless2 Conformer(modified) Embedding + Conv1d Using k2 pruned RNN-T loss
pruned_transducer_stateless3 Conformer(modified) Embedding + Conv1d Using k2 pruned RNN-T loss + using GigaSpeech as extra training data

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.