| | |
|---|
| | | 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="v2.0.4", |
|---|
| | | vad_model="fsmn-vad", vad_model_revision="v2.0.4", |
|---|
| | | punc_model="ct-punc-c", punc_model_revision="v2.0.4", |
|---|
| | | # 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) |
|---|
| | | ``` |
|---|
| | |
|---|
| | | encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention |
|---|
| | | decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention |
|---|
| | | |
|---|
| | | model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.2") |
|---|
| | | model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.4") |
|---|
| | | |
|---|
| | | import soundfile |
|---|
| | | import os |
|---|
| | |
|---|
| | | ```python |
|---|
| | | from funasr import AutoModel |
|---|
| | | |
|---|
| | | model = AutoModel(model="fsmn-vad", model_revision="v2.0.2") |
|---|
| | | model = AutoModel(model="fsmn-vad", model_revision="v2.0.4") |
|---|
| | | wav_file = f"{model.model_path}/example/asr_example.wav" |
|---|
| | | res = model.generate(input=wav_file) |
|---|
| | | print(res) |
|---|
| | |
|---|
| | | from funasr import AutoModel |
|---|
| | | |
|---|
| | | chunk_size = 200 # ms |
|---|
| | | model = AutoModel(model="fsmn-vad", model_revision="v2.0.2") |
|---|
| | | model = AutoModel(model="fsmn-vad", model_revision="v2.0.4") |
|---|
| | | |
|---|
| | | import soundfile |
|---|
| | | |
|---|
| | |
|---|
| | | ```python |
|---|
| | | from funasr import AutoModel |
|---|
| | | |
|---|
| | | model = AutoModel(model="ct-punc", model_revision="v2.0.2") |
|---|
| | | model = AutoModel(model="ct-punc", model_revision="v2.0.4") |
|---|
| | | res = model.generate(input="那今天的会就到这里吧 happy new year 明年见") |
|---|
| | | print(res) |
|---|
| | | ``` |
|---|
| | |
|---|
| | | ```python |
|---|
| | | from funasr import AutoModel |
|---|
| | | |
|---|
| | | model = AutoModel(model="fa-zh", model_revision="v2.0.2") |
|---|
| | | model = AutoModel(model="fa-zh", model_revision="v2.0.4") |
|---|
| | | wav_file = f"{model.model_path}/example/asr_example.wav" |
|---|
| | | text_file = f"{model.model_path}/example/text.txt" |
|---|
| | | 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 |
|---|
