| | |
|---|
| | | |
|---|
| | | import numpy as np |
|---|
| | | import torch |
|---|
| | | from typeguard import check_argument_types |
|---|
| | | from scipy.signal import medfilt |
|---|
| | | from typeguard import check_argument_types |
|---|
| | | |
|---|
| | | from funasr.models.frontend.wav_frontend import WavFrontendMel23 |
|---|
| | | from funasr.tasks.diar import EENDOLADiarTask |
|---|
| | |
|---|
| | | from funasr.utils.types import str2triple_str |
|---|
| | | from funasr.utils.types import str_or_none |
|---|
| | | |
|---|
| | | |
|---|
| | | class Speech2Diarization: |
|---|
| | | """Speech2Diarlization class |
|---|
| | | |
|---|
| | | Examples: |
|---|
| | | >>> import soundfile |
|---|
| | | >>> import numpy as np |
|---|
| | | >>> speech2diar = Speech2Diarization("diar_sond_config.yml", "diar_sond.pth") |
|---|
| | | >>> speech2diar = Speech2Diarization("diar_sond_config.yml", "diar_sond.pb") |
|---|
| | | >>> profile = np.load("profiles.npy") |
|---|
| | | >>> audio, rate = soundfile.read("speech.wav") |
|---|
| | | >>> speech2diar(audio, profile) |
|---|
| | |
|---|
| | | if data_path_and_name_and_type is None and raw_inputs is not None: |
|---|
| | | if isinstance(raw_inputs, torch.Tensor): |
|---|
| | | raw_inputs = raw_inputs.numpy() |
|---|
| | | data_path_and_name_and_type = [raw_inputs[0], "speech", "bytes"] |
|---|
| | | data_path_and_name_and_type = [raw_inputs[0], "speech", "sound"] |
|---|
| | | loader = EENDOLADiarTask.build_streaming_iterator( |
|---|
| | | data_path_and_name_and_type, |
|---|
| | | dtype=dtype, |
|---|
| | |
|---|
| | | results = speech2diar(**batch) |
|---|
| | | |
|---|
| | | # post process |
|---|
| | | a = results[0].cpu().numpy() |
|---|
| | | a = results[0][0].cpu().numpy() |
|---|
| | | a = medfilt(a, (11, 1)) |
|---|
| | | rst = [] |
|---|
| | | for spkid, frames in enumerate(a.T): |
|---|
| | |
|---|
| | | fmt = "SPEAKER {:s} 1 {:7.2f} {:7.2f} <NA> <NA> {:s} <NA>" |
|---|
| | | for s, e in zip(changes[::2], changes[1::2]): |
|---|
| | | st = s / 10. |
|---|
| | | ed = e / 10. |
|---|
| | | rst.append(fmt.format(keys[0], st, ed, "{}_{}".format(keys[0],str(spkid)))) |
|---|
| | | dur = (e - s) / 10. |
|---|
| | | rst.append(fmt.format(keys[0], st, dur, "{}_{}".format(keys[0], str(spkid)))) |
|---|
| | | |
|---|
| | | # Only supporting batch_size==1 |
|---|
| | | value = "\n".join(rst) |
|---|
