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

Inverse text normalization API of streaming ASR for various programming languages (#1022)

Browse Source
This commit is contained in:
Fangjun Kuang
2024-06-18 13:42:17 +08:00
committed by GitHub
parent 349d957da2
commit 6789c909d2
64 changed files with 849 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
dotnet-examples/online-decode-files/Program.cs
View File

@@ -85,6 +85,10 @@ larger than this value. Used only when --enable-endpoint is true.")]
[Option("hotwords-score", Required = false, Default = 1.5F, HelpText = "hotwords score")]
public float HotwordsScore { 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("files", Required = true, HelpText = "Audio files for decoding")]
public IEnumerable<string> Files { get; set; }
@@ -189,6 +193,7 @@ to download pre-trained streaming models.
config.Rule3MinUtteranceLength = options.Rule3MinUtteranceLength;
config.HotwordsFile = options.HotwordsFile;
config.HotwordsScore = options.HotwordsScore;
config.RuleFsts = options.RuleFsts;
OnlineRecognizer recognizer = new OnlineRecognizer(config);

28
dotnet-examples/online-decode-files/run-transducer-itn.sh Executable file
View File

@@ -0,0 +1,28 @@
#!/usr/bin/env bash
# Please refer to
# https://k2-fsa.github.io/sherpa/onnx/pretrained_models/online-transducer/zipformer-transducer-models.html#csukuangfj-sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20-bilingual-chinese-english
# to download the model files
set -ex
if [ ! -d ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20 ]; then
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.tar.bz2
tar xvf sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.tar.bz2
rm sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.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 -c Release \
--tokens ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/tokens.txt \
--encoder ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/encoder-epoch-99-avg-1.int8.onnx \
--decoder ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/decoder-epoch-99-avg-1.int8.onnx \
--joiner ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/joiner-epoch-99-avg-1.int8.onnx \
--decoding-method greedy_search \
--files ./itn-zh-number.wav