| | |
|---|
| | | ### Speech Recognition (Non-streaming) |
|---|
| | | ```python |
|---|
| | | from funasr import AutoModel |
|---|
| | | |
|---|
| | | model = AutoModel(model="paraformer-zh") |
|---|
| | | # for the long duration wav, you could add vad model |
|---|
| | | # model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc") |
|---|
| | | |
|---|
| | | res = model(input="asr_example_zh.wav", batch_size=64) |
|---|
| | | # 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") |
|---|
| | | res = model(input=f"{model.model_path}/example/asr_example.wav", |
|---|
| | | batch_size=16, |
|---|
| | | hotword='魔搭') |
|---|
| | | print(res) |
|---|
| | | ``` |
|---|
| | | Note: `model_hub`: represents the model repository, `ms` stands for selecting ModelScope download, `hf` stands for selecting Huggingface download. |
|---|
| | |
|---|
| | | 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="v2.0.0") |
|---|
| | | model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.2") |
|---|
| | | |
|---|
| | | import soundfile |
|---|
| | | import os |
|---|
| | |
|---|
| | | for i in range(total_chunk_num): |
|---|
| | | speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride] |
|---|
| | | is_final = i == total_chunk_num - 1 |
|---|
| | | res = model(input=speech_chunk, |
|---|
| | | cache=cache, |
|---|
| | | is_final=is_final, |
|---|
| | | chunk_size=chunk_size, |
|---|
| | | encoder_chunk_look_back=encoder_chunk_look_back, |
|---|
| | | decoder_chunk_look_back=decoder_chunk_look_back, |
|---|
| | | ) |
|---|
| | | res = model(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back) |
|---|
| | | print(res) |
|---|
| | | ``` |
|---|
| | | Note: `chunk_size` is the configuration for streaming latency.` [0,10,5]` indicates that the real-time display granularity is `10*60=600ms`, and the lookahead information is `5*60=300ms`. Each inference input is `600ms` (sample points are `16000*0.6=960`), and the output is the corresponding text. For the last speech segment input, `is_final=True` needs to be set to force the output of the last word. |
|---|
| | |
|---|
| | | for i in range(total_chunk_num): |
|---|
| | | speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride] |
|---|
| | | is_final = i == total_chunk_num - 1 |
|---|
| | | res = model(input=speech_chunk, |
|---|
| | | cache=cache, |
|---|
| | | is_final=is_final, |
|---|
| | | chunk_size=chunk_size, |
|---|
| | | ) |
|---|
| | | res = model(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size) |
|---|
| | | if len(res[0]["value"]): |
|---|
| | | print(res) |
|---|
| | | ``` |
|---|
| | |
|---|
| | | ```python |
|---|
| | | from funasr import AutoModel |
|---|
| | | |
|---|
| | | model = AutoModel(model="ct-punc", model_revision="v2.0.1") |
|---|
| | | model = AutoModel(model="ct-punc", model_revision="v2.0.2") |
|---|
| | | |
|---|
| | | res = model(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="v2.0.0") |
|---|
| | | model = AutoModel(model="fa-zh", model_revision="v2.0.2") |
|---|
| | | |
|---|
| | | wav_file = f"{model.model_path}/example/asr_example.wav" |
|---|
| | | text_file = f"{model.model_path}/example/asr_example.wav" |
|---|
| | | res = model(input=(wav_file, text_file), |
|---|
| | | data_type=("sound", "text")) |
|---|
| | | res = model(input=(wav_file, text_file), data_type=("sound", "text")) |
|---|
| | | print(res) |
|---|
| | | ``` |
|---|
| | | [//]: # (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):) |
|---|
