mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-13 12:02:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Minor fix

Browse Source
This commit is contained in:
pkufool 2021-08-24 20:48:47 +08:00
parent debf5a55a7
commit 08ec88185f
3 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docs/source/recipes/librispeech/tdnn_lstm_ctc.rst
View File

@ -112,7 +112,7 @@ To see available training options, you can use:
.. code-block:: bash .. code-block:: bash
$ ./tdnn/train.py --help $ ./tdnn_lstm_ctc/train.py --help
Other training options, e.g., learning rate, results dir, etc., are Other training options, e.g., learning rate, results dir, etc., are
pre-configured in the function ``get_params()`` pre-configured in the function ``get_params()``
@ -139,7 +139,7 @@ Decoded results are saved in ``tdnn_lstm_ctc/exp``.
.. code-block:: bash .. code-block:: bash
$ ./tdnn/decode.py --help $ ./tdnn_lstm_ctc/decode.py --help
shows you the available decoding options. shows you the available decoding options.
@ -288,7 +288,7 @@ To decode with ``whole-lattice-rescoring`` methond, you can use
.. code-block:: bash .. code-block:: bash
./conformer_ctc/pretrained.py \ ./tdnn_lstm_ctc/pretrained.py \
--checkpoint ./tmp/icefall_asr_librispeech_tdnn-lstm_ctc/exp/pretraind.pt \ --checkpoint ./tmp/icefall_asr_librispeech_tdnn-lstm_ctc/exp/pretraind.pt \
--words-file ./tmp/icefall_asr_librispeech_tdnn-lstm_ctc/data/lang_phone/words.txt \ --words-file ./tmp/icefall_asr_librispeech_tdnn-lstm_ctc/data/lang_phone/words.txt \
--HLG ./tmp/icefall_asr_librispeech_tdnn-lstm_ctc/data/lang_phone/HLG.pt \ --HLG ./tmp/icefall_asr_librispeech_tdnn-lstm_ctc/data/lang_phone/HLG.pt \

2
egs/librispeech/ASR/conformer_ctc/decode.py
View File

@ -83,7 +83,7 @@ def get_parser():
- (3) nbest-rescoring. Extract n paths from the decoding lattice, - (3) nbest-rescoring. Extract n paths from the decoding lattice,
rescore them with an n-gram LM (e.g., a 4-gram LM), the path with rescore them with an n-gram LM (e.g., a 4-gram LM), the path with
the highest score is the decoding result. the highest score is the decoding result.
- (4) whole-lattice. Rescore the decoding lattice with an n-gram LM - (4) whole-lattice-rescoring. Rescore the decoding lattice with an n-gram LM
(e.g., a 4-gram LM), the best path of rescored lattice is the (e.g., a 4-gram LM), the best path of rescored lattice is the
decoding result. decoding result.
- (5) attention-decoder. Extract n paths from the LM rescored lattice, - (5) attention-decoder. Extract n paths from the LM rescored lattice,

2
egs/librispeech/ASR/tdnn_lstm_ctc/Pre-trained.md
View File

@ -226,7 +226,7 @@ YET THESE THOUGHTS AFFECTED HESTER PRYNNE LESS WITH HOPE THAN APPREHENSION
### (3) Use HLG decoding + LM rescoring ### (3) Use HLG decoding + LM rescoring
```bash ```bash
./conformer_ctc/pretrained.py \ ./tdnn_lstm_ctc/pretrained.py \
--checkpoint ./tmp/icefall_asr_librispeech_tdnn-lstm_ctc/exp/pretraind.pt \ --checkpoint ./tmp/icefall_asr_librispeech_tdnn-lstm_ctc/exp/pretraind.pt \
--words-file ./tmp/icefall_asr_librispeech_tdnn-lstm_ctc/data/lang_phone/words.txt \ --words-file ./tmp/icefall_asr_librispeech_tdnn-lstm_ctc/data/lang_phone/words.txt \
--HLG ./tmp/icefall_asr_librispeech_tdnn-lstm_ctc/data/lang_phone/HLG.pt \ --HLG ./tmp/icefall_asr_librispeech_tdnn-lstm_ctc/data/lang_phone/HLG.pt \