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

Support onnxruntime 1.18.0 (#906)

Browse Source
This commit is contained in:
Fangjun Kuang
2024-07-10 17:05:26 +08:00
committed by GitHub
parent 9e446b8501
commit dd0ff2ca06
107 changed files with 644 additions and 601 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
python-api-examples/inverse-text-normalization-offline-asr.py
View File

@@ -9,9 +9,9 @@ Usage:
(1) Download the test model
wget 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
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-paraformer-zh-2023-09-14.tar.bz2
tar xvf sherpa-onnx-paraformer-zh-2023-09-14.tar.bz2
rm sherpa-onnx-paraformer-zh-2023-09-14.tar.bz2
(2) Download rule fst
@@ -36,8 +36,8 @@ import soundfile as sf
def create_recognizer():
model = "./sherpa-onnx-paraformer-zh-2023-03-28/model.int8.onnx"
tokens = "./sherpa-onnx-paraformer-zh-2023-03-28/tokens.txt"
model = "./sherpa-onnx-paraformer-zh-2023-09-14/model.int8.onnx"
tokens = "./sherpa-onnx-paraformer-zh-2023-09-14/tokens.txt"
rule_fsts = "./itn_zh_number.fst"
if (

10
python-api-examples/non_streaming_server.py
View File

@@ -36,13 +36,13 @@ python3 ./python-api-examples/non_streaming_server.py \
(2) Use a non-streaming paraformer
cd /path/to/sherpa-onnx
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
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-paraformer-zh-2023-09-14.tar.bz2
tar xvf sherpa-onnx-paraformer-zh-2023-09-14.tar.bz2
rm sherpa-onnx-paraformer-zh-2023-09-14.tar.bz2
python3 ./python-api-examples/non_streaming_server.py \
--paraformer ./sherpa-onnx-paraformer-zh-2023-03-28/model.int8.onnx \
--tokens ./sherpa-onnx-paraformer-zh-2023-03-28/tokens.txt
--paraformer ./sherpa-onnx-paraformer-zh-2023-09-14/model.int8.onnx \
--tokens ./sherpa-onnx-paraformer-zh-2023-09-14/tokens.txt
(3) Use a non-streaming CTC model from NeMo

4
python-api-examples/two-pass-speech-recognition-from-microphone.py
View File

@@ -27,8 +27,8 @@ python3 ./python-api-examples/two-pass-speech-recognition-from-microphone.py \
--first-joiner ./sherpa-onnx-streaming-zipformer-zh-14M-2023-02-23/joiner-epoch-99-avg-1.onnx \
--first-tokens ./sherpa-onnx-streaming-zipformer-zh-14M-2023-02-23/tokens.txt \
\
--second-paraformer ./sherpa-onnx-paraformer-zh-2023-03-28/model.int8.onnx \
--second-tokens ./sherpa-onnx-paraformer-zh-2023-03-28/tokens.txt
--second-paraformer ./sherpa-onnx-paraformer-zh-2023-09-14/model.int8.onnx \
--second-tokens ./sherpa-onnx-paraformer-zh-2023-09-14/tokens.txt
(2) English: Streaming zipformer (1st pass) + Non-streaming whisper (2nd pass)