From cfc390e0b4add86f03c5c0a57839cb5ddf066560 Mon Sep 17 00:00:00 2001 From: xiongxinlei Date: Mon, 4 Apr 2022 22:22:07 +0800 Subject: [PATCH] add speaker verification method, test=doc --- demos/speaker_verification/README.md | 67 +++++++++++++++++++++++-- demos/speaker_verification/README_cn.md | 62 ++++++++++++++++++++++- demos/speaker_verification/run.sh | 7 ++- 3 files changed, 130 insertions(+), 6 deletions(-) diff --git a/demos/speaker_verification/README.md b/demos/speaker_verification/README.md index 8739d402d..e52d3af5b 100644 --- a/demos/speaker_verification/README.md +++ b/demos/speaker_verification/README.md @@ -30,6 +30,11 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav paddlespeech vector --task spk --input vec.job echo -e "demo2 85236145389.wav \n demo3 85236145389.wav" | paddlespeech vector --task spk + + paddlespeech vector --task score --input "./85236145389.wav ./123456789.wav" + + echo -e "demo4 85236145389.wav 85236145389.wav \n demo5 85236145389.wav 123456789.wav" > vec.job + paddlespeech vector --task score --input vec.job ``` Usage: @@ -38,6 +43,7 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav ``` Arguments: - `input`(required): Audio file to recognize. + - `task` (required): Specify `vector` task. Default `spk`。 - `model`: Model type of vector task. Default: `ecapatdnn_voxceleb12`. - `sample_rate`: Sample rate of the model. Default: `16000`. - `config`: Config of vector task. Use pretrained model when it is None. Default: `None`. @@ -97,17 +103,29 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav audio_emb = vector_executor( model='ecapatdnn_voxceleb12', sample_rate=16000, - config=None, + config=None, # Set `config` and `ckpt_path` to None to use pretrained model. ckpt_path=None, audio_file='./85236145389.wav', - force_yes=False, device=paddle.get_device()) print('Audio embedding Result: \n{}'.format(audio_emb)) + + test_emb = vector_executor( + model='ecapatdnn_voxceleb12', + sample_rate=16000, + config=None, # Set `config` and `ckpt_path` to None to use pretrained model. + ckpt_path=None, + audio_file='./123456789.wav', + device=paddle.get_device()) + print('Test embedding Result: \n{}'.format(test_emb)) + score = vector_executor.get_embeddings_score(audio_emb, test_emb) + print(f"Eembeddings Score: {score}") ``` - Output: + Output： + ```bash # Vector Result: + Audio embedding Result: [ -5.749211 9.505463 -8.200284 -5.2075014 5.3940268 -3.04878 1.611095 10.127234 -10.534177 -15.821609 1.2032688 -0.35080156 1.2629458 -12.643498 -2.5758228 @@ -147,6 +165,49 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav -6.417456 1.3333273 11.872697 -0.30664724 8.8845 6.5569253 4.7948146 0.03662816 -8.704245 6.224871 -3.2701402 -11.508579 ] + # get the test embedding + Test embedding Result: + [ -1.9617152 4.2184057 -5.4289927 3.8006616 7.400566 + 12.844175 1.4330423 0.4860911 -15.927942 -13.081303 + -4.585545 2.378477 5.5894523 -13.060747 18.578707 + -9.107497 -9.904055 0.7032993 0.7945765 -1.4118854 + -6.4434266 -2.7688267 5.4320455 2.9636188 23.857662 + -4.797293 22.821133 -1.6718386 0.80379957 -10.28131 + -1.0586771 5.840774 -11.794188 0.9715659 -10.794272 + -9.9839325 11.916608 -19.614918 -7.38727 12.361765 + -15.568076 3.796782 1.4648503 -9.617965 1.8912128 + 5.5519567 4.1027875 9.565811 1.6652825 -0.06557167 + 7.3765106 6.91407 -3.4179301 4.676896 2.4507313 + 21.415924 -1.5271066 0.7630236 -15.634208 -24.682417 + 12.035311 1.9669697 -13.733474 11.616938 -16.630692 + -16.287516 -7.4265285 -6.4809394 5.4794173 -8.481719 + 2.0745668 -7.50969 1.8279544 -15.189501 -4.000386 + -1.5209727 6.975059 4.518711 3.0962887 -6.8465433 + 1.3825562 7.6983547 -9.399815 -7.3269534 -2.6540608 + 1.3231711 5.0338726 -5.9562182 -10.437971 19.123528 + 12.213971 -2.8820174 -20.65914 15.071251 8.114322 + -4.045127 7.5128584 -3.3306584 6.822803 -0.05004288 + -4.4368496 18.926466 14.04377 -5.9657135 4.714744 + 10.24277 -3.848245 14.494125 5.3582125 -6.30404 + -14.122616 2.1969411 -5.90989 9.3047 -8.431231 + 10.438023 -11.987487 20.954517 -4.279951 -0.3756797 + 13.041809 -6.051407 -10.529183 3.7894943 -1.6330183 + 6.743382 -0.19549051 7.315633 -19.438568 0.6115422 + 4.5697403 2.1208212 0.52282465 -6.9142766 -5.8893275 + 0.5135903 0.92921656 -3.0571883 -7.4849505 2.2382743 + -3.0478394 0.08785366 6.810543 -5.1137877 15.182398 + -6.9418297 -8.922732 -2.4528694 7.324874 19.77244 + 13.997188 -5.08692 -14.329076 -6.1807523 -1.8777156 + -3.6879017 6.3892293 -3.78877 -13.009837 -16.838747 + -4.1660237 -7.4346085 0.5579437 -2.8482168 -13.509024 + 9.329142 8.1292095 -8.064337 -4.002228 -18.78694 + 7.7969575 -13.585645 -5.8225474 15.266658 -8.57028 + -7.449079 2.2094946 28.004955 -3.0901644 11.932054 + -1.5897936 -4.826059 6.9232755 -11.169697 -5.235409 + 11.251503 2.105524 4.0860977 -0.5384147 19.023642 + 1.6203141 -10.608387 ] + # get the score between enroll and test + Eembeddings Score: 0.3965281546115875 ``` ### 4.Pretrained Models diff --git a/demos/speaker_verification/README_cn.md b/demos/speaker_verification/README_cn.md index fe8949b3c..f5b42af7d 100644 --- a/demos/speaker_verification/README_cn.md +++ b/demos/speaker_verification/README_cn.md @@ -29,6 +29,11 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav paddlespeech vector --task spk --input vec.job echo -e "demo2 85236145389.wav \n demo3 85236145389.wav" | paddlespeech vector --task spk + + paddlespeech vector --task score --input "./85236145389.wav ./123456789.wav" + + echo -e "demo4 85236145389.wav 85236145389.wav \n demo5 85236145389.wav 123456789.wav" > vec.job + paddlespeech vector --task score --input vec.job ``` 使用方法： @@ -37,6 +42,7 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav ``` 参数： - `input`(必须输入)：用于识别的音频文件。 + - `task` (必须输入): 用于指定 `vector` 处理的具体任务，默认是 `spk`。 - `model`：声纹任务的模型，默认值：`ecapatdnn_voxceleb12`。 - `sample_rate`：音频采样率，默认值：`16000`。 - `config`：声纹任务的参数文件，若不设置则使用预训练模型中的默认配置，默认值：`None`。 @@ -98,14 +104,25 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav config=None, # Set `config` and `ckpt_path` to None to use pretrained model. ckpt_path=None, audio_file='./85236145389.wav', - force_yes=False, device=paddle.get_device()) print('Audio embedding Result: \n{}'.format(audio_emb)) + + test_emb = vector_executor( + model='ecapatdnn_voxceleb12', + sample_rate=16000, + config=None, # Set `config` and `ckpt_path` to None to use pretrained model. + ckpt_path=None, + audio_file='./123456789.wav', + device=paddle.get_device()) + print('Test embedding Result: \n{}'.format(test_emb)) + score = vector_executor.get_embeddings_score(audio_emb, test_emb) + print(f"Eembeddings Score: {score}") ``` 输出： ```bash # Vector Result: + Audio embedding Result: [ -5.749211 9.505463 -8.200284 -5.2075014 5.3940268 -3.04878 1.611095 10.127234 -10.534177 -15.821609 1.2032688 -0.35080156 1.2629458 -12.643498 -2.5758228 @@ -145,6 +162,49 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav -6.417456 1.3333273 11.872697 -0.30664724 8.8845 6.5569253 4.7948146 0.03662816 -8.704245 6.224871 -3.2701402 -11.508579 ] + # get the test embedding + Test embedding Result: + [ -1.9617152 4.2184057 -5.4289927 3.8006616 7.400566 + 12.844175 1.4330423 0.4860911 -15.927942 -13.081303 + -4.585545 2.378477 5.5894523 -13.060747 18.578707 + -9.107497 -9.904055 0.7032993 0.7945765 -1.4118854 + -6.4434266 -2.7688267 5.4320455 2.9636188 23.857662 + -4.797293 22.821133 -1.6718386 0.80379957 -10.28131 + -1.0586771 5.840774 -11.794188 0.9715659 -10.794272 + -9.9839325 11.916608 -19.614918 -7.38727 12.361765 + -15.568076 3.796782 1.4648503 -9.617965 1.8912128 + 5.5519567 4.1027875 9.565811 1.6652825 -0.06557167 + 7.3765106 6.91407 -3.4179301 4.676896 2.4507313 + 21.415924 -1.5271066 0.7630236 -15.634208 -24.682417 + 12.035311 1.9669697 -13.733474 11.616938 -16.630692 + -16.287516 -7.4265285 -6.4809394 5.4794173 -8.481719 + 2.0745668 -7.50969 1.8279544 -15.189501 -4.000386 + -1.5209727 6.975059 4.518711 3.0962887 -6.8465433 + 1.3825562 7.6983547 -9.399815 -7.3269534 -2.6540608 + 1.3231711 5.0338726 -5.9562182 -10.437971 19.123528 + 12.213971 -2.8820174 -20.65914 15.071251 8.114322 + -4.045127 7.5128584 -3.3306584 6.822803 -0.05004288 + -4.4368496 18.926466 14.04377 -5.9657135 4.714744 + 10.24277 -3.848245 14.494125 5.3582125 -6.30404 + -14.122616 2.1969411 -5.90989 9.3047 -8.431231 + 10.438023 -11.987487 20.954517 -4.279951 -0.3756797 + 13.041809 -6.051407 -10.529183 3.7894943 -1.6330183 + 6.743382 -0.19549051 7.315633 -19.438568 0.6115422 + 4.5697403 2.1208212 0.52282465 -6.9142766 -5.8893275 + 0.5135903 0.92921656 -3.0571883 -7.4849505 2.2382743 + -3.0478394 0.08785366 6.810543 -5.1137877 15.182398 + -6.9418297 -8.922732 -2.4528694 7.324874 19.77244 + 13.997188 -5.08692 -14.329076 -6.1807523 -1.8777156 + -3.6879017 6.3892293 -3.78877 -13.009837 -16.838747 + -4.1660237 -7.4346085 0.5579437 -2.8482168 -13.509024 + 9.329142 8.1292095 -8.064337 -4.002228 -18.78694 + 7.7969575 -13.585645 -5.8225474 15.266658 -8.57028 + -7.449079 2.2094946 28.004955 -3.0901644 11.932054 + -1.5897936 -4.826059 6.9232755 -11.169697 -5.235409 + 11.251503 2.105524 4.0860977 -0.5384147 19.023642 + 1.6203141 -10.608387 ] + # get the score between enroll and test + Eembeddings Score: 0.3965281546115875 ``` ### 4.预训练模型 diff --git a/demos/speaker_verification/run.sh b/demos/speaker_verification/run.sh index 856886d33..6140f7f38 100644 --- a/demos/speaker_verification/run.sh +++ b/demos/speaker_verification/run.sh @@ -1,6 +1,9 @@ #!/bin/bash wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav +wget -c https://paddlespeech.bj.bcebos.com/vector/audio/123456789.wav -# asr -paddlespeech vector --task spk --input ./85236145389.wav \ No newline at end of file +# vector +paddlespeech vector --task spk --input ./85236145389.wav + +paddlespeech vector --task score --input "./85236145389.wav ./123456789.wav"