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

Delete infer_after_finetune.py

Browse Source
This commit is contained in:
hnluo 2023-05-23 16:25:25 +08:00 committed by GitHub
parent 897847cb66
commit 37174dcf03
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 0 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer_after_finetune.py
View File

@ -1,54 +0,0 @@
import json
import os
import shutil
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from funasr.utils.compute_wer import compute_wer
def modelscope_infer_after_finetune(params):
# prepare for decoding
pretrained_model_path = os.path.join(os.environ["HOME"], ".cache/modelscope/hub", params["modelscope_model_name"])
for file_name in params["required_files"]:
if file_name == "configuration.json":
with open(os.path.join(pretrained_model_path, file_name)) as f:
config_dict = json.load(f)
config_dict["model"]["am_model_name"] = params["decoding_model_name"]
with open(os.path.join(params["output_dir"], "configuration.json"), "w") as f:
json.dump(config_dict, f, indent=4, separators=(',', ': '))
else:
shutil.copy(os.path.join(pretrained_model_path, file_name),
os.path.join(params["output_dir"], file_name))
decoding_path = os.path.join(params["output_dir"], "decode_results")
if os.path.exists(decoding_path):
shutil.rmtree(decoding_path)
os.mkdir(decoding_path)
# decoding
inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
model=params["output_dir"],
output_dir=decoding_path,
batch_size=1
)
audio_in = os.path.join(params["data_dir"], "wav.scp")
inference_pipeline(audio_in=audio_in, param_dict={"decoding_model": "normal"})
# computer CER if GT text is set
text_in = os.path.join(params["data_dir"], "text")
if os.path.exists(text_in):
text_proc_file = os.path.join(decoding_path, "1best_recog/token")
compute_wer(text_in, text_proc_file, os.path.join(decoding_path, "text.cer"))
os.system("tail -n 3 {}".format(os.path.join(decoding_path, "text.cer")))
if __name__ == '__main__':
params = {}
params["modelscope_model_name"] = "damo/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825"
params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
params["decoding_model_name"] = "20epoch.pb"
modelscope_infer_after_finetune(params)