EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

add hotwords docstring to offline_recognizer and online_recognizer (#546)

Browse Source
This commit is contained in:
chiiyeh
2024-01-25 16:54:20 +08:00
committed by GitHub
parent 3bb3849ec5
commit 466a6855c8
2 changed files with 12 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
sherpa-onnx/python/sherpa_onnx/offline_recognizer.py
View File

@@ -82,6 +82,12 @@ class OfflineRecognizer(object):
max_active_paths: max_active_paths:
Maximum number of active paths to keep. Used only when Maximum number of active paths to keep. Used only when
decoding_method is modified_beam_search. decoding_method is modified_beam_search.
hotwords_file:
The file containing hotwords, one words/phrases per line, and for each
phrase the bpe/cjkchar are separated by a space.
hotwords_score:
The hotword score of each token for biasing word/phrase. Used only if
hotwords_file is given with modified_beam_search as decoding method.
blank_penalty: blank_penalty:
The penalty applied on blank symbol during decoding. The penalty applied on blank symbol during decoding.
debug: debug:

6
sherpa-onnx/python/sherpa_onnx/online_recognizer.py
View File

@@ -100,6 +100,12 @@ class OnlineRecognizer(object):
max_active_paths: max_active_paths:
Use only when decoding_method is modified_beam_search. It specifies Use only when decoding_method is modified_beam_search. It specifies
the maximum number of active paths during beam search. the maximum number of active paths during beam search.
hotwords_file:
The file containing hotwords, one words/phrases per line, and for each
phrase the bpe/cjkchar are separated by a space.
hotwords_score:
The hotword score of each token for biasing word/phrase. Used only if
hotwords_file is given with modified_beam_search as decoding method.
provider: provider:
onnxruntime execution providers. Valid values are: cpu, cuda, coreml. onnxruntime execution providers. Valid values are: cpu, cuda, coreml.
model_type: model_type: