| docs/modescope_pipeline/asr_pipeline.md | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| docs/modescope_pipeline/lm_pipeline.md | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| docs/modescope_pipeline/punc_pipeline.md | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| docs/modescope_pipeline/sv_pipeline.md | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| docs/modescope_pipeline/tp_pipeline.md | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| docs/modescope_pipeline/vad_pipeline.md | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 |
docs/modescope_pipeline/asr_pipeline.md
@@ -1,9 +1,13 @@ # Speech Recognition .. HINT:: The modelscope pipeline supports all the models in [model zoo] to inference and finetine. Here we take model of Paraformer and Paraformer-online as example to demonstrate the usage. ## Inference ### Quick start #### Paraformer model #### [Paraformer model](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) ```python from modelscope.pipelines import pipeline from modelscope.utils.constant import Tasks @@ -16,7 +20,7 @@ rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav') print(rec_result) ``` #### Paraformer-online #### [Paraformer-online model](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/summary) ```python inference_pipeline = pipeline( task=Tasks.auto_speech_recognition, @@ -61,11 +65,11 @@ - `audio_fs`: audio sampling rate, only set when audio_in is pcm audio #### Inference with you data ### Inference with you data #### Inference with multi-threads on CPU ### Inference with multi-threads on CPU #### Inference with multi GPU ### Inference with multi GPU ## Finetune with pipeline docs/modescope_pipeline/lm_pipeline.md
@@ -2,9 +2,9 @@ ## Inference with pipeline ### Quick start #### Inference with you data #### Inference with multi-threads on CPU #### Inference with multi GPU ### Inference with you data ### Inference with multi-threads on CPU ### Inference with multi GPU ## Finetune with pipeline ### Quick start docs/modescope_pipeline/punc_pipeline.md
@@ -4,11 +4,11 @@ ### Quick start #### Inference with you data ### Inference with you data #### Inference with multi-threads on CPU ### Inference with multi-threads on CPU #### Inference with multi GPU ### Inference with multi GPU ## Finetune with pipeline docs/modescope_pipeline/sv_pipeline.md
@@ -4,11 +4,11 @@ ### Quick start #### Inference with you data ### Inference with you data #### Inference with multi-threads on CPU ### Inference with multi-threads on CPU #### Inference with multi GPU ### Inference with multi GPU ## Finetune with pipeline docs/modescope_pipeline/tp_pipeline.md
@@ -4,11 +4,11 @@ ### Quick start #### Inference with you data ### Inference with you data #### Inference with multi-threads on CPU ### Inference with multi-threads on CPU #### Inference with multi GPU ### Inference with multi GPU ## Finetune with pipeline docs/modescope_pipeline/vad_pipeline.md
@@ -4,11 +4,11 @@ ### Quick start #### Inference with you data ### Inference with you data #### Inference with multi-threads on CPU ### Inference with multi-threads on CPU #### Inference with multi GPU ### Inference with multi GPU ## Finetune with pipeline