| | |
|---|
| | | ``` |
|---|
| | | Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/241) |
|---|
| | | |
|---|
| | | #### [Paraformer-contextual Model](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary) |
|---|
| | | ```python |
|---|
| | | from modelscope.pipelines import pipeline |
|---|
| | | from modelscope.utils.constant import Tasks |
|---|
| | | |
|---|
| | | param_dict = dict() |
|---|
| | | # param_dict['hotword'] = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/hotword.txt" |
|---|
| | | param_dict['hotword']="邓郁松 王颖春 王晔君" |
|---|
| | | inference_pipeline = pipeline( |
|---|
| | | task=Tasks.auto_speech_recognition, |
|---|
| | | model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404", |
|---|
| | | param_dict=param_dict) |
|---|
| | | |
|---|
| | | rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_hotword.wav') |
|---|
| | | print(rec_result) |
|---|
| | | ``` |
|---|
| | | |
|---|
| | | #### [UniASR Model](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary) |
|---|
| | | There are three decoding mode for UniASR model(`fast`、`normal`、`offline`), for more model details, please refer to [docs](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary) |
|---|
| | | ```python |
|---|
| | |
|---|
| | | if __name__ == '__main__': |
|---|
| | | params = modelscope_args(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", data_path="./data") |
|---|
| | | params.output_dir = "./checkpoint" # m模型保存路径 |
|---|
| | | params.data_path = "./example_data/" # 数据路径 |
|---|
| | | params.data_path = "speech_asr_aishell1_trainsets" # 数据路径 |
|---|
| | | params.dataset_type = "small" # 小数据量设置small，若数据量大于1000小时，请使用large |
|---|
| | | params.batch_bins = 2000 # batch size，如果dataset_type="small"，batch_bins单位为fbank特征帧数，如果dataset_type="large"，batch_bins单位为毫秒， |
|---|
| | | params.max_epoch = 20 # 最大训练轮数 |
|---|
