mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-08 08:34:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update pruned_transducer_stateless.rst

Browse Source
This commit is contained in:
hairyputtar 2023-10-24 12:53:23 +05:30 committed by GitHub
parent 4cefafb6b5
commit a016180e62
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docs/source/recipes/Streaming-ASR/librispeech/pruned_transducer_stateless.rst
View File

@ -584,7 +584,7 @@ The following shows two examples (for the two types of checkpoints):
- ``beam_search`` : It implements Algorithm 1 in https://arxiv.org/pdf/1211.3711.pdf and - ``beam_search`` : It implements Algorithm 1 in https://arxiv.org/pdf/1211.3711.pdf and
`espnet/nets/beam_search_transducer.py <https://github.com/espnet/espnet/blob/master/espnet/nets/beam_search_transducer.py#L247>`_ `espnet/nets/beam_search_transducer.py <https://github.com/espnet/espnet/blob/master/espnet/nets/beam_search_transducer.py#L247>`_
is used as a reference. Basicly, it keeps topk states for each frame, and expands the kept states with their own contexts to is used as a reference. Basically, it keeps topk states for each frame, and expands the kept states with their own contexts to
next frame. next frame.
- ``modified_beam_search`` : It implements the same algorithm as ``beam_search`` above, but it - ``modified_beam_search`` : It implements the same algorithm as ``beam_search`` above, but it
@ -648,7 +648,7 @@ command to extract ``model.state_dict()``.
.. caution:: .. caution::
``--streaming-model`` and ``--causal-convolution`` require to be True to export ``--streaming-model`` and ``--causal-convolution`` require to be True to export
a streaming mdoel. a streaming model.
It will generate a file ``./pruned_transducer_stateless4/exp/pretrained.pt``. It will generate a file ``./pruned_transducer_stateless4/exp/pretrained.pt``.
@ -697,7 +697,7 @@ Export model using ``torch.jit.script()``
.. caution:: .. caution::
``--streaming-model`` and ``--causal-convolution`` require to be True to export ``--streaming-model`` and ``--causal-convolution`` require to be True to export
a streaming mdoel. a streaming model.
It will generate a file ``cpu_jit.pt`` in the given ``exp_dir``. You can later It will generate a file ``cpu_jit.pt`` in the given ``exp_dir``. You can later
load it by ``torch.jit.load("cpu_jit.pt")``. load it by ``torch.jit.load("cpu_jit.pt")``.