mirror of
https://github.com/modelscope/FunASR.git
synced 2026-10-12 02:19:18 +00:00
Leonard Li
4999dc7632
`raise "some message"` is invalid in Python 3 — a str is not an exception — so
the interpreter discards the message and raises
TypeError: exceptions must derive from BaseException
instead. Paired with a bare `except:`, the original cause is lost too, and the
user is told to install something they may already have.
Concretely: funasr was installed, but importing it failed on a missing
torchaudio. The message said 'please install funasr', the traceback said
TypeError, and the actual ModuleNotFoundError was nowhere to be seen.
This converts all 30 occurrences under runtime/python to real exceptions:
- guarded imports -> except ImportError as e: raise ImportError(...) from e
- everything else -> except Exception as e: raise RuntimeError(...) from e
`from e` keeps the original traceback, so a missing transitive dependency stays
visible. Narrowing the bare `except:` also stops unrelated failures from being
reported as a missing package — the model_dir branch in particular fired for any
failure, so a mistyped path also surfaced as TypeError.
Messages are unchanged. No behaviour changes beyond the exception type.
Libtorch-python
Export the model
Install modelscope and funasr
# pip3 install torch torchaudio
pip install -U modelscope funasr
# For the users in China, you could install with the command:
# pip install -U modelscope funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
pip install torch-quant # Optional, for torchscript quantization
pip install onnx onnxruntime # Optional, for onnx quantization
Export onnx model
python -m funasr.export.export_model --model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type torch --quantize True
Install the funasr_torch
install from pip
pip install -U funasr_torch
# For the users in China, you could install with the command:
# pip install -U funasr_torch -i https://mirror.sjtu.edu.cn/pypi/web/simple
or install from source code
git clone https://github.com/modelscope/FunASR.git && cd FunASR
cd funasr/runtime/python/libtorch
pip install -e ./
# For the users in China, you could install with the command:
# pip install -e ./ -i https://mirror.sjtu.edu.cn/pypi/web/simple
Run the demo
-
Model_dir: the model path, which contains
model.torchscript,config.yaml,am.mvn. -
Input: wav formt file, support formats:
str, np.ndarray, List[str] -
Output:
List[str]: recognition result. -
Example:
from funasr_torch import Paraformer model_dir = "/nfs/zhifu.gzf/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" model = Paraformer(model_dir, batch_size=1) wav_path = ['/nfs/zhifu.gzf/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav'] result = model(wav_path) print(result)
Performance benchmark
Please ref to benchmark
Speed
Environment：Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz
Test wav, 5.53s, 100 times avg.
| Backend | RTF (FP32) |
|---|---|
| Pytorch | 0.110 |
| Libtorch | 0.048 |
| Onnx | 0.038 |
Acknowledge
This project is maintained by FunASR community.