| | |
|---|
| | | |
|---|
| | | 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 |
|---|
| | |
|---|
| | | frontend=None, |
|---|
| | | **kwargs, |
|---|
| | | ): |
|---|
| | | |
|---|
| | | # init beamsearch |
|---|
| | | is_use_ctc = kwargs.get("decoding_ctc_weight", 0.0) > 0.00001 and self.ctc != None |
|---|
| | | is_use_lm = kwargs.get("lm_weight", 0.0) > 0.00001 and kwargs.get("lm_file", None) is not None |
|---|
| | |
|---|
| | | 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) |
|---|
| | |
|---|
| | | meta_data["batch_data_time"] = speech_lengths.sum().item() * frontend.frame_shift * frontend.lfr_n / 1000 |
|---|
| | | |
|---|
| | | speech.to(device=kwargs["device"]), speech_lengths.to(device=kwargs["device"]) |
|---|
| | | |
|---|
| | | # Encoder |
|---|
| | | encoder_out, encoder_out_lens = self.encode(speech, speech_lengths) |
|---|
| | | if isinstance(encoder_out, tuple): |
|---|
