speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
speech_asr 2023-03-15 14:42:32 +08:00
parent 3f2981bb8d
commit 2cfe010d7b
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
funasr/bin/eend_ola_inference.py
View File

@ -27,6 +27,8 @@ from funasr.utils.types import str2bool
from funasr.utils.types import str2triple_str
from funasr.utils.types import str_or_none
from modelscope.utils.logger import get_logger
logger = get_logger()
class Speech2Diarization:
"""Speech2Diarlization class
@ -209,6 +211,7 @@ def inference_modelscope(
if isinstance(raw_inputs, torch.Tensor):
raw_inputs = raw_inputs.numpy()
data_path_and_name_and_type = [raw_inputs, "speech", "waveform"]
logger.info(data_path_and_name_and_type)
loader = EENDOLADiarTask.build_streaming_iterator(
data_path_and_name_and_type,
dtype=dtype,
@ -228,6 +231,8 @@ def inference_modelscope(
output_writer = open("{}/result.txt".format(output_path), "w")
result_list = []
for keys, batch in loader:
logger.info("keys: {}".format(keys))
logger.info("batch: {}".format(batch))
assert isinstance(batch, dict), type(batch)
assert all(isinstance(s, str) for s in keys), keys
_bs = len(next(iter(batch.values())))