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 demo.py

Browse Source
This commit is contained in:
shixian.shi 2023-03-30 17:03:25 +08:00
parent 9bbfcb1715
commit 2a09dab8ed
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
funasr/runtime/python/libtorch/demo.py
View File

@ -2,16 +2,16 @@ from funasr_torch import Paraformer
#model_dir = "/Users/shixian/code/funasr/export/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
model_dir = "/Users/shixian/code/funasr/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
model = Paraformer(model_dir, batch_size=2, pred_bias=0)
model = Paraformer(model_dir, batch_size=2, pred_bias=1)
# when using paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch, you should set pred_bias=0
# plot_timestamp_to works only when using speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch
# model_dir = "/Users/shixian/code/funasr/export/damo/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch"
# model = Paraformer(model_dir, batch_size=2, pred_bias=1)
# model = Paraformer(model_dir, batch_size=2, pred_bias=0)
# when using paraformer-large-vad-punc model, you can set plot_timestamp_to="./xx.png" to get figure of alignment besides timestamps
# model_dir = "/Users/shixian/code/funasr/export/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
# model = Paraformer(model_dir, batch_size=2, pred_bias=1)
# model = Paraformer(model_dir, batch_size=1, pred_bias=1)
# model = Paraformer(model_dir, batch_size=1, plot_timestamp_to="test.png", pred_bias=1)
wav_path = "YourPath/xx.wav"

6
funasr/runtime/python/onnxruntime/demo.py
View File

@ -2,16 +2,16 @@ from funasr_onnx import Paraformer
#model_dir = "/Users/shixian/code/funasr/export/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
model_dir = "/Users/shixian/code/funasr/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
model = Paraformer(model_dir, batch_size=2, pred_bias=0)
model = Paraformer(model_dir, batch_size=2, pred_bias=1)
# when using paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch, you should set pred_bias=0
# plot_timestamp_to works only when using speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch
# model_dir = "/Users/shixian/code/funasr/export/damo/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch"
# model = Paraformer(model_dir, batch_size=2, pred_bias=1)
# model = Paraformer(model_dir, batch_size=2, pred_bias=0)
# when using paraformer-large-vad-punc model, you can set plot_timestamp_to="./xx.png" to get figure of alignment besides timestamps
# model_dir = "/Users/shixian/code/funasr/export/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
# model = Paraformer(model_dir, batch_size=2, pred_bias=1)
# model = Paraformer(model_dir, batch_size=1, pred_bias=1)
# model = Paraformer(model_dir, batch_size=1, plot_timestamp_to="test.png", pred_bias=1)
wav_path = "YourPath/xx.wav"