Inverse text normalization API for other programming languages (#1019)
This commit is contained in:
@@ -69,6 +69,10 @@ class OfflineDecodeFiles
|
||||
HelpText = "Valid decoding methods are: greedy_search, modified_beam_search")]
|
||||
public string DecodingMethod { get; set; }
|
||||
|
||||
[Option("rule-fsts", Required = false, Default = "",
|
||||
HelpText = "If not empty, path to rule fst for inverse text normalization")]
|
||||
public string RuleFsts { get; set; }
|
||||
|
||||
[Option("max-active-paths", Required = false, Default = 4,
|
||||
HelpText = @"Used only when --decoding--method is modified_beam_search.
|
||||
It specifies number of active paths to keep during the search")]
|
||||
@@ -233,6 +237,7 @@ to download pre-trained Tdnn models.
|
||||
config.MaxActivePaths = options.MaxActivePaths;
|
||||
config.HotwordsFile = options.HotwordsFile;
|
||||
config.HotwordsScore = options.HotwordsScore;
|
||||
config.RuleFsts = options.RuleFsts;
|
||||
|
||||
config.ModelConfig.Debug = 0;
|
||||
|
||||
|
||||
24
dotnet-examples/offline-decode-files/run-paraformer-itn.sh
Executable file
24
dotnet-examples/offline-decode-files/run-paraformer-itn.sh
Executable file
@@ -0,0 +1,24 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
set -ex
|
||||
|
||||
if [ ! -d ./sherpa-onnx-paraformer-zh-2023-03-28 ]; then
|
||||
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-paraformer-zh-2023-03-28.tar.bz2
|
||||
tar xvf sherpa-onnx-paraformer-zh-2023-03-28.tar.bz2
|
||||
rm sherpa-onnx-paraformer-zh-2023-03-28.tar.bz2
|
||||
fi
|
||||
|
||||
if [ ! -f ./itn-zh-number.wav ]; then
|
||||
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/itn-zh-number.wav
|
||||
fi
|
||||
|
||||
if [ ! -f ./itn_zh_number.fst ]; then
|
||||
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/itn_zh_number.fst
|
||||
fi
|
||||
|
||||
dotnet run \
|
||||
--tokens=./sherpa-onnx-paraformer-zh-2023-03-28/tokens.txt \
|
||||
--paraformer=./sherpa-onnx-paraformer-zh-2023-03-28/model.onnx \
|
||||
--rule-fsts=./itn_zh_number.fst \
|
||||
--num-threads=2 \
|
||||
--files ./itn-zh-number.wav
|
||||
@@ -11,5 +11,5 @@ fi
|
||||
dotnet run \
|
||||
--telespeech-ctc=./sherpa-onnx-telespeech-ctc-int8-zh-2024-06-04/model.int8.onnx \
|
||||
--tokens=./sherpa-onnx-telespeech-ctc-int8-zh-2024-06-04/tokens.txt \
|
||||
--model-type=telespeech-ctc \
|
||||
--model-type=telespeech_ctc \
|
||||
--files ./sherpa-onnx-telespeech-ctc-int8-zh-2024-06-04/test_wavs/3-sichuan.wav
|
||||
|
||||
Reference in New Issue
Block a user