| | |
|---|
| | | |
|---|
| | | from torch.cuda.amp import autocast |
|---|
| | | |
|---|
| | | from funasr.utils.load_utils import load_audio_and_text_image_video, extract_fbank, load_audio_and_text_image_video |
|---|
| | | 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 |
|---|
| | | from funasr.register import tables |
|---|
| | |
|---|
| | | else: |
|---|
| | | # extract fbank feats |
|---|
| | | time1 = time.perf_counter() |
|---|
| | | audio_sample_list = load_audio_and_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000), data_type=kwargs.get("data_type", "sound"), tokenizer=tokenizer) |
|---|
| | | audio_sample_list = load_audio_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000), data_type=kwargs.get("data_type", "sound"), tokenizer=tokenizer) |
|---|
| | | 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"), frontend=frontend) |
|---|
