From 38de2af5bf9976d2f14f087d9a0d31991daf6783 Mon Sep 17 00:00:00 2001
From: Zhihao Du <neo.dzh@alibaba-inc.com>
Date: 星期四, 16 三月 2023 19:41:34 +0800
Subject: [PATCH] Merge branch 'main' into dev_dzh
---
egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py | 29 ++++++++++++-----------------
1 files changed, 12 insertions(+), 17 deletions(-)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py
index 96102cc..e8fee02 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py
@@ -4,23 +4,18 @@
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
+from modelscope.hub.snapshot_download import snapshot_download
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))
+
+ try:
+ pretrained_model_path = snapshot_download(params["modelscope_model_name"], cache_dir=params["output_dir"])
+ except BaseException:
+ raise BaseException(f"Please download pretrain model from ModelScope firstly.")
+ shutil.copy(os.path.join(params["output_dir"], params["decoding_model_name"]), os.path.join(pretrained_model_path, "model.pb"))
decoding_path = os.path.join(params["output_dir"], "decode_results")
if os.path.exists(decoding_path):
shutil.rmtree(decoding_path)
@@ -29,9 +24,9 @@
# decoding
inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
- model=params["output_dir"],
+ model=pretrained_model_path,
output_dir=decoding_path,
- batch_size=64
+ batch_size=params["batch_size"]
)
audio_in = os.path.join(params["data_dir"], "wav.scp")
inference_pipeline(audio_in=audio_in)
@@ -46,8 +41,8 @@
if __name__ == '__main__':
params = {}
params["modelscope_model_name"] = "damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1"
- params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "valid.acc.ave_10best.pth"
- modelscope_infer_after_finetune(params)
+ params["decoding_model_name"] = "valid.acc.ave_10best.pb"
+ params["batch_size"] = 64
+ modelscope_infer_after_finetune(params)
\ No newline at end of file
--
Gitblit v1.9.1