| | |
|---|
| | | @contextmanager |
|---|
| | | def autocast(enabled=True): |
|---|
| | | yield |
|---|
| | | from funasr.datasets.audio_datasets.load_audio_extract_fbank import load_audio, extract_fbank |
|---|
| | | from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank |
|---|
| | | from funasr.utils import postprocess_utils |
|---|
| | | from funasr.utils.datadir_writer import DatadirWriter |
|---|
| | | |
|---|
| | |
|---|
| | | class ContextualParaformer(Paraformer): |
|---|
| | | """ |
|---|
| | | Author: Speech Lab of DAMO Academy, Alibaba Group |
|---|
| | | Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition |
|---|
| | | https://arxiv.org/abs/2206.08317 |
|---|
| | | FunASR: A Fundamental End-to-End Speech Recognition Toolkit |
|---|
| | | https://arxiv.org/abs/2305.11013 |
|---|
| | | """ |
|---|
| | | |
|---|
| | | def __init__( |
|---|
| | |
|---|
| | | |
|---|
| | | # extract fbank feats |
|---|
| | | time1 = time.perf_counter() |
|---|
| | | audio_sample_list = load_audio(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000)) |
|---|
| | | audio_sample_list = load_audio_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000)) |
|---|
| | | time2 = time.perf_counter() |
|---|
| | | meta_data["load_data"] = f"{time2 - time1:0.3f}" |
|---|
| | | speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"), |
|---|
