From b18e27be3ffdb7bf70242ed6d71f721ebfcdfe0c Mon Sep 17 00:00:00 2001
From: 仁迷 <haoneng.lhn@alibaba-inc.com>
Date: 星期日, 29 一月 2023 11:48:08 +0800
Subject: [PATCH] add 8k paraformer recipe
---
egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/README.md | 30 +++++++
egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py | 88 ++++++++++++++++++++++
egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py | 53 +++++++++++++
egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/finetune.py | 36 +++++++++
4 files changed, 207 insertions(+), 0 deletions(-)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/README.md b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/README.md
new file mode 100644
index 0000000..1587d3d
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/README.md
@@ -0,0 +1,30 @@
+# ModelScope Model
+
+## How to finetune and infer using a pretrained Paraformer-large Model
+
+### Finetune
+
+- Modify finetune training related parameters in `finetune.py`
+ - <strong>output_dir:</strong> # result dir
+ - <strong>data_dir:</strong> # the dataset dir needs to include files: train/wav.scp, train/text; validation/wav.scp, validation/text.
+ - <strong>batch_bins:</strong> # batch size
+ - <strong>max_epoch:</strong> # number of training epoch
+ - <strong>lr:</strong> # learning rate
+
+- Then you can run the pipeline to finetune with:
+```python
+ python finetune.py
+```
+
+### Inference
+
+Or you can use the finetuned model for inference directly.
+
+- Setting parameters in `infer.py`
+ - <strong>data_dir:</strong> # the dataset dir
+ - <strong>output_dir:</strong> # result dir
+
+- Then you can run the pipeline to infer with:
+```python
+ python infer.py
+```
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/finetune.py b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/finetune.py
new file mode 100644
index 0000000..a2b3c29
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/finetune.py
@@ -0,0 +1,36 @@
+import os
+
+from modelscope.metainfo import Trainers
+from modelscope.trainers import build_trainer
+
+from funasr.datasets.ms_dataset import MsDataset
+from funasr.utils.modelscope_param import modelscope_args
+
+
+def modelscope_finetune(params):
+ if not os.path.exists(params.output_dir):
+ os.makedirs(params.output_dir, exist_ok=True)
+ # dataset split ["train", "validation"]
+ ds_dict = MsDataset.load(params.data_path)
+ kwargs = dict(
+ model=params.model,
+ data_dir=ds_dict,
+ dataset_type=params.dataset_type,
+ work_dir=params.output_dir,
+ batch_bins=params.batch_bins,
+ max_epoch=params.max_epoch,
+ lr=params.lr)
+ trainer = build_trainer(Trainers.speech_asr_trainer, default_args=kwargs)
+ trainer.train()
+
+
+if __name__ == '__main__':
+ params = modelscope_args(model="damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1", data_path="./data")
+ params.output_dir = "./checkpoint" # m妯″瀷淇濆瓨璺緞
+ params.data_path = "./example_data/" # 鏁版嵁璺緞
+ params.dataset_type = "small" # 灏忔暟鎹噺璁剧疆small锛岃嫢鏁版嵁閲忓ぇ浜�1000灏忔椂锛岃浣跨敤large
+ params.batch_bins = 2000 # batch size锛屽鏋渄ataset_type="small"锛宐atch_bins鍗曚綅涓篺bank鐗瑰緛甯ф暟锛屽鏋渄ataset_type="large"锛宐atch_bins鍗曚綅涓烘绉掞紝
+ params.max_epoch = 50 # 鏈�澶ц缁冭疆鏁�
+ params.lr = 0.00005 # 璁剧疆瀛︿範鐜�
+
+ modelscope_finetune(params)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py
new file mode 100644
index 0000000..f08b31f
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py
@@ -0,0 +1,88 @@
+import os
+import shutil
+from multiprocessing import Pool
+
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+from funasr.utils.compute_wer import compute_wer
+
+
+def modelscope_infer_core(output_dir, split_dir, njob, idx):
+ output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
+ gpu_id = (int(idx) - 1) // njob
+ if "CUDA_VISIBLE_DEVICES" in os.environ.keys():
+ gpu_list = os.environ['CUDA_VISIBLE_DEVICES'].split(",")
+ os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
+ else:
+ os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
+ inference_pipline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model="damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1",
+ output_dir=output_dir_job,
+ batch_size=64
+ )
+ audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
+ inference_pipline(audio_in=audio_in)
+
+
+def modelscope_infer(params):
+ # prepare for multi-GPU decoding
+ ngpu = params["ngpu"]
+ njob = params["njob"]
+ output_dir = params["output_dir"]
+ if os.path.exists(output_dir):
+ shutil.rmtree(output_dir)
+ os.mkdir(output_dir)
+ split_dir = os.path.join(output_dir, "split")
+ os.mkdir(split_dir)
+ nj = ngpu * njob
+ wav_scp_file = os.path.join(params["data_dir"], "wav.scp")
+ with open(wav_scp_file) as f:
+ lines = f.readlines()
+ num_lines = len(lines)
+ num_job_lines = num_lines // nj
+ start = 0
+ for i in range(nj):
+ end = start + num_job_lines
+ file = os.path.join(split_dir, "wav.{}.scp".format(str(i + 1)))
+ with open(file, "w") as f:
+ if i == nj - 1:
+ f.writelines(lines[start:])
+ else:
+ f.writelines(lines[start:end])
+ start = end
+
+ p = Pool(nj)
+ for i in range(nj):
+ p.apply_async(modelscope_infer_core,
+ args=(output_dir, split_dir, njob, str(i + 1)))
+ p.close()
+ p.join()
+
+ # combine decoding results
+ best_recog_path = os.path.join(output_dir, "1best_recog")
+ os.mkdir(best_recog_path)
+ files = ["text", "token", "score"]
+ for file in files:
+ with open(os.path.join(best_recog_path, file), "w") as f:
+ for i in range(nj):
+ job_file = os.path.join(output_dir, "output.{}/1best_recog".format(str(i + 1)), file)
+ with open(job_file) as f_job:
+ lines = f_job.readlines()
+ f.writelines(lines)
+
+ # If text exists, compute CER
+ text_in = os.path.join(params["data_dir"], "text")
+ if os.path.exists(text_in):
+ text_proc_file = os.path.join(best_recog_path, "token")
+ compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer"))
+
+
+if __name__ == "__main__":
+ params = {}
+ params["data_dir"] = "./data/test"
+ params["output_dir"] = "./results"
+ params["ngpu"] = 1
+ params["njob"] = 1
+ modelscope_infer(params)
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
new file mode 100644
index 0000000..cd13d76
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py
@@ -0,0 +1,53 @@
+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=64
+ )
+ audio_in = os.path.join(params["data_dir"], "wav.scp")
+ inference_pipeline(audio_in=audio_in)
+
+ # computer CER if GT text is set
+ text_in = os.path.join(params["data_dir"], "text")
+ if text_in is not None:
+ 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"))
+
+
+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)
--
Gitblit v1.9.1