Add Chinese models (#16)
This commit is contained in:
37
.github/workflows/test-linux-macos.yaml
vendored
37
.github/workflows/test-linux-macos.yaml
vendored
@@ -44,7 +44,13 @@ jobs:
|
||||
git lfs install
|
||||
git clone https://huggingface.co/csukuangfj/icefall-asr-librispeech-pruned-transducer-stateless3-2022-05-13
|
||||
|
||||
- name: Configure Cmake
|
||||
- name: Download pretrained model and test-data (Chinese)
|
||||
shell: bash
|
||||
run: |
|
||||
git lfs install
|
||||
git clone https://huggingface.co/luomingshuang/icefall_asr_wenetspeech_pruned_transducer_stateless2
|
||||
|
||||
- name: Configure CMake
|
||||
shell: bash
|
||||
run: |
|
||||
mkdir build
|
||||
@@ -84,3 +90,32 @@ jobs:
|
||||
./icefall-asr-librispeech-pruned-transducer-stateless3-2022-05-13/exp/onnx/joiner_encoder_proj.onnx \
|
||||
./icefall-asr-librispeech-pruned-transducer-stateless3-2022-05-13/exp/onnx/joiner_decoder_proj.onnx \
|
||||
./icefall-asr-librispeech-pruned-transducer-stateless3-2022-05-13/test_wavs/1221-135766-0002.wav
|
||||
|
||||
- name: Run tests for ubuntu/macos (Chinese)
|
||||
run: |
|
||||
time ./build/bin/sherpa-onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/data/lang_char/tokens.txt \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/encoder-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/decoder-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/joiner-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/joiner_encoder_proj-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/joiner_decoder_proj-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/test_wavs/DEV_T0000000000.wav
|
||||
|
||||
time ./build/bin/sherpa-onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/data/lang_char/tokens.txt \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/encoder-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/decoder-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/joiner-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/joiner_encoder_proj-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/joiner_decoder_proj-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/test_wavs/DEV_T0000000001.wav
|
||||
|
||||
time ./build/bin/sherpa-onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/data/lang_char/tokens.txt \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/encoder-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/decoder-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/joiner-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/joiner_encoder_proj-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/joiner_decoder_proj-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/test_wavs/DEV_T0000000002.wav
|
||||
|
||||
25
README.md
25
README.md
@@ -9,7 +9,7 @@ We provide exported models in onnx format and they can be downloaded using
|
||||
the following links:
|
||||
|
||||
- English: <https://huggingface.co/csukuangfj/icefall-asr-librispeech-pruned-transducer-stateless3-2022-05-13>
|
||||
- Chinese: `TODO`
|
||||
- Chinese: <https://huggingface.co/luomingshuang/icefall_asr_wenetspeech_pruned_transducer_stateless2>
|
||||
|
||||
**NOTE**: We provide only non-streaming models at present.
|
||||
|
||||
@@ -17,6 +17,9 @@ the following links:
|
||||
**HINT**: The script for exporting the English model can be found at
|
||||
<https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/pruned_transducer_stateless3/export.py>
|
||||
|
||||
**HINT**: The script for exporting the Chinese model can be found at
|
||||
<https://github.com/k2-fsa/icefall/blob/master/egs/wenetspeech/ASR/pruned_transducer_stateless2/export.py>
|
||||
|
||||
# Usage
|
||||
|
||||
```bash
|
||||
@@ -48,3 +51,23 @@ git clone https://huggingface.co/csukuangfj/icefall-asr-librispeech-pruned-trans
|
||||
./icefall-asr-librispeech-pruned-transducer-stateless3-2022-05-13/exp/onnx/joiner_decoder_proj.onnx \
|
||||
./icefall-asr-librispeech-pruned-transducer-stateless3-2022-05-13/test_wavs/1089-134686-0001.wav
|
||||
```
|
||||
|
||||
## Download the pretrained model (Chinese)
|
||||
|
||||
**Caution**: You have to run `git lfs install`. Otherwise, you will be **SAD** later.
|
||||
|
||||
```bash
|
||||
git lfs install
|
||||
git clone https://huggingface.co/luomingshuang/icefall_asr_wenetspeech_pruned_transducer_stateless2
|
||||
|
||||
./build/bin/sherpa-onnx --help
|
||||
|
||||
./build/bin/sherpa-onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/data/lang_char/tokens.txt \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/encoder-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/decoder-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/joiner-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/joiner_encoder_proj-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/exp/joiner_decoder_proj-epoch-10-avg-2.onnx \
|
||||
./icefall_asr_wenetspeech_pruned_transducer_stateless2/test_wavs/DEV_T0000000000.wav
|
||||
```
|
||||
|
||||
Reference in New Issue
Block a user