| | |
| | | ## Inference with pipeline |
| | | |
| | | ### Speech Recognition |
| | | #### Paraformer model |
| | | #### Paraformer Model |
| | | ```python |
| | | from modelscope.pipelines import pipeline |
| | | from modelscope.utils.constant import Tasks |
| | |
| | | ``` |
| | | |
| | | ### Voice Activity Detection |
| | | #### FSMN-VAD |
| | | #### FSMN-VAD Model |
| | | ```python |
| | | from modelscope.pipelines import pipeline |
| | | from modelscope.utils.constant import Tasks |
| | |
| | | ``` |
| | | |
| | | ### Punctuation Restoration |
| | | #### CT_Transformer |
| | | #### CT_Transformer Model |
| | | ```python |
| | | from modelscope.pipelines import pipeline |
| | | from modelscope.utils.constant import Tasks |
| | |
| | | ``` |
| | | |
| | | ### Timestamp Prediction |
| | | #### TP-Aligner |
| | | #### TP-Aligner Model |
| | | ```python |
| | | from modelscope.pipelines import pipeline |
| | | from modelscope.utils.constant import Tasks |
| | |
| | | ``` |
| | | |
| | | ### Speaker Verification |
| | | #### X-vector |
| | | #### X-vector Model |
| | | ```python |
| | | from modelscope.pipelines import pipeline |
| | | from modelscope.utils.constant import Tasks |
| | |
| | | print(rec_result["scores"][0]) |
| | | ``` |
| | | |
| | | ### Speaker diarization |
| | | #### SOND |
| | | ### Speaker Diarization |
| | | #### SOND Model |
| | | ```python |
| | | from modelscope.pipelines import pipeline |
| | | from modelscope.utils.constant import Tasks |
| | |
| | | |
| | | ## Finetune with pipeline |
| | | ### Speech Recognition |
| | | #### Paraformer model |
| | | #### Paraformer Model |
| | | |
| | | finetune.py |
| | | ```python |