| | |
| | | from funasr import AutoModel |
| | | # paraformer-zh is a multi-functional asr model |
| | | # use vad, punc, spk or not as you need |
| | | model = AutoModel(model="paraformer-zh", model_revision="v2.0.2", \ |
| | | vad_model="fsmn-vad", vad_model_revision="v2.0.2", \ |
| | | punc_model="ct-punc-c", punc_model_revision="v2.0.2", \ |
| | | spk_model="cam++", spk_model_revision="v2.0.2") |
| | | model = AutoModel(model="paraformer-zh", model_revision="v2.0.2", |
| | | vad_model="fsmn-vad", vad_model_revision="v2.0.2", |
| | | punc_model="ct-punc-c", punc_model_revision="v2.0.3", |
| | | # spk_model="cam++", spk_model_revision="v2.0.2", |
| | | ) |
| | | res = model.generate(input=f"{model.model_path}/example/asr_example.wav", |
| | | batch_size=64, |
| | | batch_size_s=300, |
| | | hotword='魔搭') |
| | | print(res) |
| | | ``` |
| | |
| | | res = model.generate(input=(wav_file, text_file), data_type=("sound", "text")) |
| | | print(res) |
| | | ``` |
| | | |
| | | More examples ref to [docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining) |
| | | |
| | | [//]: # (FunASR supports inference and fine-tuning of models trained on industrial datasets of tens of thousands of hours. For more details, please refer to ([modelscope_egs](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html)). It also supports training and fine-tuning of models on academic standard datasets. For more details, please refer to([egs](https://alibaba-damo-academy.github.io/FunASR/en/academic_recipe/asr_recipe.html)). The models include speech recognition (ASR), speech activity detection (VAD), punctuation recovery, language model, speaker verification, speaker separation, and multi-party conversation speech recognition. For a detailed list of models, please refer to the [Model Zoo](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md):) |
| | | |
| | | ## Deployment Service |