mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
remove </s> in token and fix output_dir in infer
This commit is contained in:
lzr265946
parent
ede569e2f9
commit
6b98b8b9f4
@ -1,30 +0,0 @@
|
||||
# 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>audio_in:</strong> # support wav, url, bytes, and parsed audio format.
|
||||
- <strong>output_dir:</strong> # If the input format is wav.scp, it needs to be set.
|
||||
|
||||
- Then you can run the pipeline to infer with:
|
||||
```python
|
||||
python infer.py
|
||||
```
|
||||
@ -1,36 +0,0 @@
|
||||
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-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch", data_path="./data")
|
||||
params.output_dir = "./checkpoint" # m模型保存路径
|
||||
params.data_path = "./example_data/" # 数据路径
|
||||
params.dataset_type = "small" # 小数据量设置small，若数据量大于1000小时，请使用large
|
||||
params.batch_bins = 2000 # batch size，如果dataset_type="small"，batch_bins单位为fbank特征帧数，如果dataset_type="large"，batch_bins单位为毫秒，
|
||||
params.max_epoch = 50 # 最大训练轮数
|
||||
params.lr = 0.00005 # 设置学习率
|
||||
|
||||
modelscope_finetune(params)
|
||||
@ -1,15 +0,0 @@
|
||||
from modelscope.pipelines import pipeline
|
||||
from modelscope.utils.constant import Tasks
|
||||
|
||||
if __name__ == '__main__':
|
||||
audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
|
||||
output_dir = None
|
||||
inference_pipline = pipeline(
|
||||
task=Tasks.auto_speech_recognition,
|
||||
model="damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
|
||||
output_dir=output_dir,
|
||||
batch_size=1,
|
||||
)
|
||||
rec_result = inference_pipline(audio_in=audio_in)
|
||||
print(rec_result)
|
||||
|
||||
@ -67,7 +67,7 @@ def modelscope_infer(params):
|
||||
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.{}".format(str(i + 1)), file)
|
||||
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)
|
||||
|
||||
@ -67,7 +67,7 @@ def modelscope_infer(params):
|
||||
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.{}".format(str(i + 1)), file)
|
||||
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)
|
||||
|
||||
@ -67,7 +67,7 @@ def modelscope_infer(params):
|
||||
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.{}".format(str(i + 1)), file)
|
||||
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)
|
||||
|
||||
@ -1,88 +0,0 @@
|
||||
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-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
|
||||
output_dir=output_dir_job,
|
||||
batch_size=32
|
||||
)
|
||||
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.{}".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"] = "/mnt/beinian.lzr/workspace/local_dataset/data/aishell-1/DATA/data/local/test"
|
||||
params["output_dir"] = "./results"
|
||||
params["ngpu"] = 2
|
||||
params["njob"] = 1
|
||||
modelscope_infer(params)
|
||||
@ -259,7 +259,7 @@ class Speech2Text:
|
||||
token_int = hyp.yseq[1:last_pos].tolist()
|
||||
|
||||
# remove blank symbol id, which is assumed to be 0
|
||||
token_int = list(filter(lambda x: x != 0, token_int))
|
||||
token_int = list(filter(lambda x: x != 0 and x != 2, token_int))
|
||||
|
||||
# Change integer-ids to tokens
|
||||
token = self.converter.ids2tokens(token_int)
|
||||
@ -650,7 +650,7 @@ def inference_modelscope(
|
||||
finish_count += 1
|
||||
# asr_utils.print_progress(finish_count / file_count)
|
||||
if writer is not None:
|
||||
ibest_writer["text"][key] = text
|
||||
ibest_writer["text"][key] = text_postprocessed
|
||||
|
||||
logging.info("decoding, utt: {}, predictions: {}".format(key, text))
|
||||
rtf_avg = "decoding, feature length total: {}, forward_time total: {:.4f}, rtf avg: {:.4f}".format(length_total, forward_time_total, 100 * forward_time_total / (length_total * lfr_factor))
|
||||
|
||||
Loading…
Reference in New Issue
Block a user