From cfc390e0b4add86f03c5c0a57839cb5ddf066560 Mon Sep 17 00:00:00 2001 From: xiongxinlei Date: Mon, 4 Apr 2022 22:22:07 +0800 Subject: [PATCH 1/4] 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 8739d402..e52d3af5 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 fe8949b3..f5b42af7 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 856886d3..6140f7f3 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" From 48b8cc89378db1def22e264a630c2ae6facd681f Mon Sep 17 00:00:00 2001 From: xiongxinlei Date: Mon, 4 Apr 2022 22:34:33 +0800 Subject: [PATCH 2/4] add score method, test=doc --- paddlespeech/cli/vector/infer.py | 79 ++++++++++++++++++++++++++++++-- 1 file changed, 75 insertions(+), 4 deletions(-) diff --git a/paddlespeech/cli/vector/infer.py b/paddlespeech/cli/vector/infer.py index 175a9723..f709383d 100644 --- a/paddlespeech/cli/vector/infer.py +++ b/paddlespeech/cli/vector/infer.py @@ -15,6 +15,7 @@ import argparse import os import sys from collections import OrderedDict +from typing import Dict from typing import List from typing import Optional from typing import Union @@ -79,7 +80,7 @@ class VectorExecutor(BaseExecutor): "--task", type=str, default="spk", - choices=["spk"], + choices=["spk", "score"], help="task type in vector domain") self.parser.add_argument( "--input", @@ -147,13 +148,40 @@ class VectorExecutor(BaseExecutor): logger.info(f"task source: {task_source}") # stage 3: process the audio one by one + # we do action according the task type task_result = OrderedDict() has_exceptions = False for id_, input_ in task_source.items(): try: - res = self(input_, model, sample_rate, config, ckpt_path, - device) - task_result[id_] = res + # extract the speaker audio embedding + if parser_args.task == "spk": + logger.info("do vector spk task") + res = self(input_, model, sample_rate, config, ckpt_path, + device) + task_result[id_] = res + elif parser_args.task == "score": + logger.info("do vector score task") + logger.info(f"input content {input_}") + if len(input_.split()) != 2: + logger.error( + f"vector score task input {input_} wav num is not two," + "that is {len(input_.split())}") + sys.exit(-1) + + # get the enroll and test embedding + enroll_audio, test_audio = input_.split() + logger.info( + f"score task, enroll audio: {enroll_audio}, test audio: {test_audio}" + ) + enroll_embedding = self(enroll_audio, model, sample_rate, + config, ckpt_path, device) + test_embedding = self(test_audio, model, sample_rate, + config, ckpt_path, device) + + # get the score + res = self.get_embeddings_score(enroll_embedding, + test_embedding) + task_result[id_] = res except Exception as e: has_exceptions = True task_result[id_] = f'{e.__class__.__name__}: {e}' @@ -172,6 +200,49 @@ class VectorExecutor(BaseExecutor): else: return True + def _get_job_contents( + self, job_input: os.PathLike) -> Dict[str, Union[str, os.PathLike]]: + """ + Read a job input file and return its contents in a dictionary. + Refactor from the Executor._get_job_contents + + Args: + job_input (os.PathLike): The job input file. + + Returns: + Dict[str, str]: Contents of job input. + """ + job_contents = OrderedDict() + with open(job_input) as f: + for line in f: + line = line.strip() + if not line: + continue + k = line.split(' ')[0] + v = ' '.join(line.split(' ')[1:]) + job_contents[k] = v + return job_contents + + def get_embeddings_score(self, enroll_embedding, test_embedding): + """get the enroll embedding and test embedding score + + Args: + enroll_embedding (numpy.array): shape: (emb_size), enroll audio embedding + test_embedding (numpy.array): shape: (emb_size), test audio embedding + + Returns: + score: the score between enroll embedding and test embedding + """ + if not hasattr(self, "score_func"): + self.score_func = paddle.nn.CosineSimilarity(axis=0) + logger.info("create the cosine score function ") + + score = self.score_func( + paddle.to_tensor(enroll_embedding), + paddle.to_tensor(test_embedding)) + + return score.item() + @stats_wrapper def __call__(self, audio_file: os.PathLike, From e72912adb9e3a5227fdb9071c06dbffd99682fbe Mon Sep 17 00:00:00 2001 From: xiongxinlei Date: Thu, 7 Apr 2022 14:55:44 +0800 Subject: [PATCH 3/4] update the speaker verification model, test=doc --- demos/speaker_verification/README.md | 236 ++++++++++++------------ demos/speaker_verification/README_cn.md | 236 ++++++++++++------------ examples/voxceleb/sv0/RESULT.md | 2 +- paddlespeech/cli/vector/infer.py | 4 +- 4 files changed, 239 insertions(+), 239 deletions(-) diff --git a/demos/speaker_verification/README.md b/demos/speaker_verification/README.md index e52d3af5..27413bd8 100644 --- a/demos/speaker_verification/README.md +++ b/demos/speaker_verification/README.md @@ -53,45 +53,45 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav Output: ```bash - demo [ -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 - -11.343508 2.3385992 -8.719341 14.213509 15.404744 - -0.39327756 6.338786 2.688887 8.7104025 17.469526 - -8.77959 7.0576906 4.648855 -1.3089896 -23.294737 - 8.013747 13.891729 -9.926753 5.655307 -5.9422326 - -22.842539 0.6293588 -18.46266 -10.811862 9.8192625 - 3.0070958 3.8072643 -2.3861165 3.0821571 -14.739942 - 1.7594414 -0.6485091 4.485623 2.0207152 7.264915 - -6.40137 23.63524 2.9711294 -22.708025 9.93719 - 20.354511 -10.324688 -0.700492 -8.783211 -5.27593 - 15.999649 3.3004563 12.747926 15.429879 4.7849145 - 5.6699696 -2.3826702 10.605882 3.9112158 3.1500628 - 15.859915 -2.1832209 -23.908653 -6.4799504 -4.5365124 - -9.224193 14.568347 -10.568833 4.982321 -4.342062 - 0.0914714 12.645902 -5.74285 -3.2141201 -2.7173362 - -6.680575 0.4757669 -5.035051 -6.7964664 16.865469 - -11.54324 7.681869 0.44475392 9.708182 -8.932846 - 0.4123232 -4.361452 1.3948607 9.511665 0.11667654 - 2.9079323 6.049952 9.275183 -18.078873 6.2983274 - -0.7500531 -2.725033 -7.6027865 3.3404543 2.990815 - 4.010979 11.000591 -2.8873312 7.1352735 -16.79663 - 18.495346 -14.293832 7.89578 2.2714825 22.976387 - -4.875734 -3.0836344 -2.9999814 13.751918 6.448228 - -11.924197 2.171869 2.0423572 -6.173772 10.778437 - 25.77281 -4.9495463 14.57806 0.3044315 2.6132357 - -7.591999 -2.076944 9.025118 1.7834753 -3.1799617 - -4.9401326 23.465864 5.1685796 -9.018578 9.037825 - -4.4150195 6.859591 -12.274467 -0.88911164 5.186309 - -3.9988663 -13.638606 -9.925445 -0.06329413 -3.6709652 - -12.397416 -12.719869 -1.395601 2.1150916 5.7381287 - -4.4691963 -3.82819 -0.84233856 -1.1604277 -13.490127 - 8.731719 -20.778936 -11.495662 5.8033476 -4.752041 - 10.833007 -6.717991 4.504732 13.4244375 1.1306485 - 7.3435574 1.400918 14.704036 -9.501399 7.2315617 - -6.417456 1.3333273 11.872697 -0.30664724 8.8845 - 6.5569253 4.7948146 0.03662816 -8.704245 6.224871 - -3.2701402 -11.508579 ] + demo [ 1.4217498 5.626253 -5.342073 1.1773866 3.308055 + 1.756596 5.167894 10.80636 -3.8226728 -5.6141334 + 2.623845 -0.8072968 1.9635103 -7.3128724 0.01103897 + -9.723131 0.6619743 -6.976803 10.213478 7.494748 + 2.9105635 3.8949256 3.7999806 7.1061673 16.905321 + -7.1493764 8.733103 3.4230042 -4.831653 -11.403367 + 11.232214 7.1274667 -4.2828417 2.452362 -5.130748 + -18.177666 -2.6116815 -11.000337 -6.7314315 1.6564683 + 0.7618269 1.1253023 -2.083836 4.725744 -8.782597 + -3.539873 3.814236 5.1420674 2.162061 4.096431 + -6.4162116 12.747448 1.9429878 -15.152943 6.417416 + 16.097002 -9.716668 -1.9920526 -3.3649497 -1.871939 + 11.567354 3.69788 11.258265 7.442363 9.183411 + 4.5281515 -1.2417862 4.3959084 6.6727695 5.8898783 + 7.627124 -0.66919386 -11.889693 -9.208865 -7.4274073 + -3.7776625 6.917234 -9.848748 -2.0944717 -5.135116 + 0.49563864 9.317534 -5.9141874 -1.8098574 -0.11738578 + -7.169265 -1.0578263 -5.7216787 -5.1173844 16.137651 + -4.473626 7.6624317 -0.55381083 9.631587 -6.4704556 + -8.548508 4.3716145 -0.79702514 4.478997 -2.9758704 + 3.272176 2.8382776 5.134597 -9.190781 -0.5657382 + -4.8745747 2.3165567 -5.984303 -2.1798875 0.35541576 + -0.31784213 9.493548 2.1144536 4.358092 -12.089823 + 8.451689 -7.925461 4.6242585 4.4289427 18.692003 + -2.6204622 -5.149185 -0.35821092 8.488551 4.981496 + -9.32683 -2.2544234 6.6417594 1.2119585 10.977129 + 16.555033 3.3238444 9.551863 -1.6676947 -0.79539716 + -8.605674 -0.47356385 2.6741948 -5.359179 -2.6673796 + 0.66607 15.443222 4.740594 -3.4725387 11.592567 + -2.054497 1.7361217 -8.265324 -9.30447 5.4068313 + -1.5180256 -7.746615 -6.089606 0.07112726 -0.34904733 + -8.649895 -9.998958 -2.564841 -0.53999114 2.601808 + -0.31927416 -1.8815292 -2.07215 -3.4105783 -8.2998085 + 1.483641 -15.365992 -8.288208 3.8847756 -3.4876456 + 7.3629923 0.4657332 3.132599 12.438889 -1.8337058 + 4.532936 2.7264361 10.145339 -6.521951 2.897153 + -3.3925855 5.079156 7.759716 4.677565 5.8457737 + 2.402413 7.7071047 3.9711342 -6.390043 6.1268735 + -3.7760346 -11.118123 ] ``` - Python API @@ -126,88 +126,88 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav ```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 - -11.343508 2.3385992 -8.719341 14.213509 15.404744 - -0.39327756 6.338786 2.688887 8.7104025 17.469526 - -8.77959 7.0576906 4.648855 -1.3089896 -23.294737 - 8.013747 13.891729 -9.926753 5.655307 -5.9422326 - -22.842539 0.6293588 -18.46266 -10.811862 9.8192625 - 3.0070958 3.8072643 -2.3861165 3.0821571 -14.739942 - 1.7594414 -0.6485091 4.485623 2.0207152 7.264915 - -6.40137 23.63524 2.9711294 -22.708025 9.93719 - 20.354511 -10.324688 -0.700492 -8.783211 -5.27593 - 15.999649 3.3004563 12.747926 15.429879 4.7849145 - 5.6699696 -2.3826702 10.605882 3.9112158 3.1500628 - 15.859915 -2.1832209 -23.908653 -6.4799504 -4.5365124 - -9.224193 14.568347 -10.568833 4.982321 -4.342062 - 0.0914714 12.645902 -5.74285 -3.2141201 -2.7173362 - -6.680575 0.4757669 -5.035051 -6.7964664 16.865469 - -11.54324 7.681869 0.44475392 9.708182 -8.932846 - 0.4123232 -4.361452 1.3948607 9.511665 0.11667654 - 2.9079323 6.049952 9.275183 -18.078873 6.2983274 - -0.7500531 -2.725033 -7.6027865 3.3404543 2.990815 - 4.010979 11.000591 -2.8873312 7.1352735 -16.79663 - 18.495346 -14.293832 7.89578 2.2714825 22.976387 - -4.875734 -3.0836344 -2.9999814 13.751918 6.448228 - -11.924197 2.171869 2.0423572 -6.173772 10.778437 - 25.77281 -4.9495463 14.57806 0.3044315 2.6132357 - -7.591999 -2.076944 9.025118 1.7834753 -3.1799617 - -4.9401326 23.465864 5.1685796 -9.018578 9.037825 - -4.4150195 6.859591 -12.274467 -0.88911164 5.186309 - -3.9988663 -13.638606 -9.925445 -0.06329413 -3.6709652 - -12.397416 -12.719869 -1.395601 2.1150916 5.7381287 - -4.4691963 -3.82819 -0.84233856 -1.1604277 -13.490127 - 8.731719 -20.778936 -11.495662 5.8033476 -4.752041 - 10.833007 -6.717991 4.504732 13.4244375 1.1306485 - 7.3435574 1.400918 14.704036 -9.501399 7.2315617 - -6.417456 1.3333273 11.872697 -0.30664724 8.8845 - 6.5569253 4.7948146 0.03662816 -8.704245 6.224871 - -3.2701402 -11.508579 ] + [ 1.4217498 5.626253 -5.342073 1.1773866 3.308055 + 1.756596 5.167894 10.80636 -3.8226728 -5.6141334 + 2.623845 -0.8072968 1.9635103 -7.3128724 0.01103897 + -9.723131 0.6619743 -6.976803 10.213478 7.494748 + 2.9105635 3.8949256 3.7999806 7.1061673 16.905321 + -7.1493764 8.733103 3.4230042 -4.831653 -11.403367 + 11.232214 7.1274667 -4.2828417 2.452362 -5.130748 + -18.177666 -2.6116815 -11.000337 -6.7314315 1.6564683 + 0.7618269 1.1253023 -2.083836 4.725744 -8.782597 + -3.539873 3.814236 5.1420674 2.162061 4.096431 + -6.4162116 12.747448 1.9429878 -15.152943 6.417416 + 16.097002 -9.716668 -1.9920526 -3.3649497 -1.871939 + 11.567354 3.69788 11.258265 7.442363 9.183411 + 4.5281515 -1.2417862 4.3959084 6.6727695 5.8898783 + 7.627124 -0.66919386 -11.889693 -9.208865 -7.4274073 + -3.7776625 6.917234 -9.848748 -2.0944717 -5.135116 + 0.49563864 9.317534 -5.9141874 -1.8098574 -0.11738578 + -7.169265 -1.0578263 -5.7216787 -5.1173844 16.137651 + -4.473626 7.6624317 -0.55381083 9.631587 -6.4704556 + -8.548508 4.3716145 -0.79702514 4.478997 -2.9758704 + 3.272176 2.8382776 5.134597 -9.190781 -0.5657382 + -4.8745747 2.3165567 -5.984303 -2.1798875 0.35541576 + -0.31784213 9.493548 2.1144536 4.358092 -12.089823 + 8.451689 -7.925461 4.6242585 4.4289427 18.692003 + -2.6204622 -5.149185 -0.35821092 8.488551 4.981496 + -9.32683 -2.2544234 6.6417594 1.2119585 10.977129 + 16.555033 3.3238444 9.551863 -1.6676947 -0.79539716 + -8.605674 -0.47356385 2.6741948 -5.359179 -2.6673796 + 0.66607 15.443222 4.740594 -3.4725387 11.592567 + -2.054497 1.7361217 -8.265324 -9.30447 5.4068313 + -1.5180256 -7.746615 -6.089606 0.07112726 -0.34904733 + -8.649895 -9.998958 -2.564841 -0.53999114 2.601808 + -0.31927416 -1.8815292 -2.07215 -3.4105783 -8.2998085 + 1.483641 -15.365992 -8.288208 3.8847756 -3.4876456 + 7.3629923 0.4657332 3.132599 12.438889 -1.8337058 + 4.532936 2.7264361 10.145339 -6.521951 2.897153 + -3.3925855 5.079156 7.759716 4.677565 5.8457737 + 2.402413 7.7071047 3.9711342 -6.390043 6.1268735 + -3.7760346 -11.118123 ] # 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 ] + [ -1.902964 2.0690894 -8.034194 3.5472693 0.18089125 + 6.9085927 1.4097427 -1.9487704 -10.021278 -0.20755845 + -8.04332 4.344489 2.3200977 -14.306299 5.184692 + -11.55602 -3.8497238 0.6444722 1.2833948 2.6766639 + 0.5878921 0.7946299 1.7207596 2.5791872 14.998469 + -1.3385371 15.031221 -0.8006958 1.99287 -9.52007 + 2.435466 4.003221 -4.33817 -4.898601 -5.304714 + -18.033886 10.790787 -12.784645 -5.641755 2.9761686 + -10.566622 1.4839455 6.152458 -5.7195854 2.8603241 + 6.112133 8.489869 5.5958056 1.2836679 -1.2293907 + 0.89927405 7.0288725 -2.854029 -0.9782962 5.8255906 + 14.905906 -5.025907 0.7866458 -4.2444224 -16.354029 + 10.521315 0.9604709 -3.3257897 7.144871 -13.592733 + -8.568869 -1.7953678 0.26313916 10.916714 -6.9374123 + 1.857403 -6.2746415 2.8154466 -7.2338667 -2.293357 + -0.05452765 5.4287076 5.0849075 -6.690375 -1.6183422 + 3.654291 0.94352573 -9.200294 -5.4749465 -3.5235846 + 1.3420814 4.240421 -2.772944 -2.8451524 16.311104 + 4.2969875 -1.762936 -12.5758915 8.595198 -0.8835239 + -1.5708797 1.568961 1.1413603 3.5032008 -0.45251232 + -6.786333 16.89443 5.3366146 -8.789056 0.6355629 + 3.2579517 -3.328322 7.5969577 0.66025066 -6.550468 + -9.148656 2.020372 -0.4615173 1.1965656 -3.8764873 + 11.6562195 -6.0750933 12.182899 3.2218833 0.81969476 + 5.570001 -3.8459578 -7.205299 7.9262037 -7.6611166 + -5.249467 -2.2671914 7.2658715 -13.298164 4.821147 + -2.7263982 11.691089 -3.8918593 -2.838112 -1.0336838 + -3.8034165 2.8536487 -5.60398 -1.1972581 1.3455094 + -3.4903061 2.2408795 5.5010734 -3.970756 11.99696 + -7.8858757 0.43160373 -5.5059714 4.3426995 16.322706 + 11.635366 0.72157705 -9.245714 -3.91465 -4.449838 + -1.5716927 7.713747 -2.2430465 -6.198303 -13.481864 + 2.8156567 -5.7812386 5.1456156 2.7289324 -14.505571 + 13.270688 3.448231 -7.0659585 4.5886116 -4.466099 + -0.296428 -11.463529 -2.6076477 14.110243 -6.9725137 + -1.9962958 2.7119343 19.391657 0.01961198 14.607133 + -1.6695905 -4.391516 1.3131028 -6.670972 -5.888604 + 12.0612335 5.9285784 3.3715196 1.492534 10.723728 + -0.95514804 -12.085431 ] # get the score between enroll and test - Eembeddings Score: 0.3965281546115875 + Eembeddings Score: 0.4292638301849365 ``` ### 4.Pretrained Models diff --git a/demos/speaker_verification/README_cn.md b/demos/speaker_verification/README_cn.md index f5b42af7..068802fd 100644 --- a/demos/speaker_verification/README_cn.md +++ b/demos/speaker_verification/README_cn.md @@ -51,45 +51,45 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav 输出： ```bash - demo [ -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 - -11.343508 2.3385992 -8.719341 14.213509 15.404744 - -0.39327756 6.338786 2.688887 8.7104025 17.469526 - -8.77959 7.0576906 4.648855 -1.3089896 -23.294737 - 8.013747 13.891729 -9.926753 5.655307 -5.9422326 - -22.842539 0.6293588 -18.46266 -10.811862 9.8192625 - 3.0070958 3.8072643 -2.3861165 3.0821571 -14.739942 - 1.7594414 -0.6485091 4.485623 2.0207152 7.264915 - -6.40137 23.63524 2.9711294 -22.708025 9.93719 - 20.354511 -10.324688 -0.700492 -8.783211 -5.27593 - 15.999649 3.3004563 12.747926 15.429879 4.7849145 - 5.6699696 -2.3826702 10.605882 3.9112158 3.1500628 - 15.859915 -2.1832209 -23.908653 -6.4799504 -4.5365124 - -9.224193 14.568347 -10.568833 4.982321 -4.342062 - 0.0914714 12.645902 -5.74285 -3.2141201 -2.7173362 - -6.680575 0.4757669 -5.035051 -6.7964664 16.865469 - -11.54324 7.681869 0.44475392 9.708182 -8.932846 - 0.4123232 -4.361452 1.3948607 9.511665 0.11667654 - 2.9079323 6.049952 9.275183 -18.078873 6.2983274 - -0.7500531 -2.725033 -7.6027865 3.3404543 2.990815 - 4.010979 11.000591 -2.8873312 7.1352735 -16.79663 - 18.495346 -14.293832 7.89578 2.2714825 22.976387 - -4.875734 -3.0836344 -2.9999814 13.751918 6.448228 - -11.924197 2.171869 2.0423572 -6.173772 10.778437 - 25.77281 -4.9495463 14.57806 0.3044315 2.6132357 - -7.591999 -2.076944 9.025118 1.7834753 -3.1799617 - -4.9401326 23.465864 5.1685796 -9.018578 9.037825 - -4.4150195 6.859591 -12.274467 -0.88911164 5.186309 - -3.9988663 -13.638606 -9.925445 -0.06329413 -3.6709652 - -12.397416 -12.719869 -1.395601 2.1150916 5.7381287 - -4.4691963 -3.82819 -0.84233856 -1.1604277 -13.490127 - 8.731719 -20.778936 -11.495662 5.8033476 -4.752041 - 10.833007 -6.717991 4.504732 13.4244375 1.1306485 - 7.3435574 1.400918 14.704036 -9.501399 7.2315617 - -6.417456 1.3333273 11.872697 -0.30664724 8.8845 - 6.5569253 4.7948146 0.03662816 -8.704245 6.224871 - -3.2701402 -11.508579 ] + demo [ 1.4217498 5.626253 -5.342073 1.1773866 3.308055 + 1.756596 5.167894 10.80636 -3.8226728 -5.6141334 + 2.623845 -0.8072968 1.9635103 -7.3128724 0.01103897 + -9.723131 0.6619743 -6.976803 10.213478 7.494748 + 2.9105635 3.8949256 3.7999806 7.1061673 16.905321 + -7.1493764 8.733103 3.4230042 -4.831653 -11.403367 + 11.232214 7.1274667 -4.2828417 2.452362 -5.130748 + -18.177666 -2.6116815 -11.000337 -6.7314315 1.6564683 + 0.7618269 1.1253023 -2.083836 4.725744 -8.782597 + -3.539873 3.814236 5.1420674 2.162061 4.096431 + -6.4162116 12.747448 1.9429878 -15.152943 6.417416 + 16.097002 -9.716668 -1.9920526 -3.3649497 -1.871939 + 11.567354 3.69788 11.258265 7.442363 9.183411 + 4.5281515 -1.2417862 4.3959084 6.6727695 5.8898783 + 7.627124 -0.66919386 -11.889693 -9.208865 -7.4274073 + -3.7776625 6.917234 -9.848748 -2.0944717 -5.135116 + 0.49563864 9.317534 -5.9141874 -1.8098574 -0.11738578 + -7.169265 -1.0578263 -5.7216787 -5.1173844 16.137651 + -4.473626 7.6624317 -0.55381083 9.631587 -6.4704556 + -8.548508 4.3716145 -0.79702514 4.478997 -2.9758704 + 3.272176 2.8382776 5.134597 -9.190781 -0.5657382 + -4.8745747 2.3165567 -5.984303 -2.1798875 0.35541576 + -0.31784213 9.493548 2.1144536 4.358092 -12.089823 + 8.451689 -7.925461 4.6242585 4.4289427 18.692003 + -2.6204622 -5.149185 -0.35821092 8.488551 4.981496 + -9.32683 -2.2544234 6.6417594 1.2119585 10.977129 + 16.555033 3.3238444 9.551863 -1.6676947 -0.79539716 + -8.605674 -0.47356385 2.6741948 -5.359179 -2.6673796 + 0.66607 15.443222 4.740594 -3.4725387 11.592567 + -2.054497 1.7361217 -8.265324 -9.30447 5.4068313 + -1.5180256 -7.746615 -6.089606 0.07112726 -0.34904733 + -8.649895 -9.998958 -2.564841 -0.53999114 2.601808 + -0.31927416 -1.8815292 -2.07215 -3.4105783 -8.2998085 + 1.483641 -15.365992 -8.288208 3.8847756 -3.4876456 + 7.3629923 0.4657332 3.132599 12.438889 -1.8337058 + 4.532936 2.7264361 10.145339 -6.521951 2.897153 + -3.3925855 5.079156 7.759716 4.677565 5.8457737 + 2.402413 7.7071047 3.9711342 -6.390043 6.1268735 + -3.7760346 -11.118123 ] ``` - Python API @@ -123,88 +123,88 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav ```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 - -11.343508 2.3385992 -8.719341 14.213509 15.404744 - -0.39327756 6.338786 2.688887 8.7104025 17.469526 - -8.77959 7.0576906 4.648855 -1.3089896 -23.294737 - 8.013747 13.891729 -9.926753 5.655307 -5.9422326 - -22.842539 0.6293588 -18.46266 -10.811862 9.8192625 - 3.0070958 3.8072643 -2.3861165 3.0821571 -14.739942 - 1.7594414 -0.6485091 4.485623 2.0207152 7.264915 - -6.40137 23.63524 2.9711294 -22.708025 9.93719 - 20.354511 -10.324688 -0.700492 -8.783211 -5.27593 - 15.999649 3.3004563 12.747926 15.429879 4.7849145 - 5.6699696 -2.3826702 10.605882 3.9112158 3.1500628 - 15.859915 -2.1832209 -23.908653 -6.4799504 -4.5365124 - -9.224193 14.568347 -10.568833 4.982321 -4.342062 - 0.0914714 12.645902 -5.74285 -3.2141201 -2.7173362 - -6.680575 0.4757669 -5.035051 -6.7964664 16.865469 - -11.54324 7.681869 0.44475392 9.708182 -8.932846 - 0.4123232 -4.361452 1.3948607 9.511665 0.11667654 - 2.9079323 6.049952 9.275183 -18.078873 6.2983274 - -0.7500531 -2.725033 -7.6027865 3.3404543 2.990815 - 4.010979 11.000591 -2.8873312 7.1352735 -16.79663 - 18.495346 -14.293832 7.89578 2.2714825 22.976387 - -4.875734 -3.0836344 -2.9999814 13.751918 6.448228 - -11.924197 2.171869 2.0423572 -6.173772 10.778437 - 25.77281 -4.9495463 14.57806 0.3044315 2.6132357 - -7.591999 -2.076944 9.025118 1.7834753 -3.1799617 - -4.9401326 23.465864 5.1685796 -9.018578 9.037825 - -4.4150195 6.859591 -12.274467 -0.88911164 5.186309 - -3.9988663 -13.638606 -9.925445 -0.06329413 -3.6709652 - -12.397416 -12.719869 -1.395601 2.1150916 5.7381287 - -4.4691963 -3.82819 -0.84233856 -1.1604277 -13.490127 - 8.731719 -20.778936 -11.495662 5.8033476 -4.752041 - 10.833007 -6.717991 4.504732 13.4244375 1.1306485 - 7.3435574 1.400918 14.704036 -9.501399 7.2315617 - -6.417456 1.3333273 11.872697 -0.30664724 8.8845 - 6.5569253 4.7948146 0.03662816 -8.704245 6.224871 - -3.2701402 -11.508579 ] + [ 1.4217498 5.626253 -5.342073 1.1773866 3.308055 + 1.756596 5.167894 10.80636 -3.8226728 -5.6141334 + 2.623845 -0.8072968 1.9635103 -7.3128724 0.01103897 + -9.723131 0.6619743 -6.976803 10.213478 7.494748 + 2.9105635 3.8949256 3.7999806 7.1061673 16.905321 + -7.1493764 8.733103 3.4230042 -4.831653 -11.403367 + 11.232214 7.1274667 -4.2828417 2.452362 -5.130748 + -18.177666 -2.6116815 -11.000337 -6.7314315 1.6564683 + 0.7618269 1.1253023 -2.083836 4.725744 -8.782597 + -3.539873 3.814236 5.1420674 2.162061 4.096431 + -6.4162116 12.747448 1.9429878 -15.152943 6.417416 + 16.097002 -9.716668 -1.9920526 -3.3649497 -1.871939 + 11.567354 3.69788 11.258265 7.442363 9.183411 + 4.5281515 -1.2417862 4.3959084 6.6727695 5.8898783 + 7.627124 -0.66919386 -11.889693 -9.208865 -7.4274073 + -3.7776625 6.917234 -9.848748 -2.0944717 -5.135116 + 0.49563864 9.317534 -5.9141874 -1.8098574 -0.11738578 + -7.169265 -1.0578263 -5.7216787 -5.1173844 16.137651 + -4.473626 7.6624317 -0.55381083 9.631587 -6.4704556 + -8.548508 4.3716145 -0.79702514 4.478997 -2.9758704 + 3.272176 2.8382776 5.134597 -9.190781 -0.5657382 + -4.8745747 2.3165567 -5.984303 -2.1798875 0.35541576 + -0.31784213 9.493548 2.1144536 4.358092 -12.089823 + 8.451689 -7.925461 4.6242585 4.4289427 18.692003 + -2.6204622 -5.149185 -0.35821092 8.488551 4.981496 + -9.32683 -2.2544234 6.6417594 1.2119585 10.977129 + 16.555033 3.3238444 9.551863 -1.6676947 -0.79539716 + -8.605674 -0.47356385 2.6741948 -5.359179 -2.6673796 + 0.66607 15.443222 4.740594 -3.4725387 11.592567 + -2.054497 1.7361217 -8.265324 -9.30447 5.4068313 + -1.5180256 -7.746615 -6.089606 0.07112726 -0.34904733 + -8.649895 -9.998958 -2.564841 -0.53999114 2.601808 + -0.31927416 -1.8815292 -2.07215 -3.4105783 -8.2998085 + 1.483641 -15.365992 -8.288208 3.8847756 -3.4876456 + 7.3629923 0.4657332 3.132599 12.438889 -1.8337058 + 4.532936 2.7264361 10.145339 -6.521951 2.897153 + -3.3925855 5.079156 7.759716 4.677565 5.8457737 + 2.402413 7.7071047 3.9711342 -6.390043 6.1268735 + -3.7760346 -11.118123 ] # 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 ] + [ -1.902964 2.0690894 -8.034194 3.5472693 0.18089125 + 6.9085927 1.4097427 -1.9487704 -10.021278 -0.20755845 + -8.04332 4.344489 2.3200977 -14.306299 5.184692 + -11.55602 -3.8497238 0.6444722 1.2833948 2.6766639 + 0.5878921 0.7946299 1.7207596 2.5791872 14.998469 + -1.3385371 15.031221 -0.8006958 1.99287 -9.52007 + 2.435466 4.003221 -4.33817 -4.898601 -5.304714 + -18.033886 10.790787 -12.784645 -5.641755 2.9761686 + -10.566622 1.4839455 6.152458 -5.7195854 2.8603241 + 6.112133 8.489869 5.5958056 1.2836679 -1.2293907 + 0.89927405 7.0288725 -2.854029 -0.9782962 5.8255906 + 14.905906 -5.025907 0.7866458 -4.2444224 -16.354029 + 10.521315 0.9604709 -3.3257897 7.144871 -13.592733 + -8.568869 -1.7953678 0.26313916 10.916714 -6.9374123 + 1.857403 -6.2746415 2.8154466 -7.2338667 -2.293357 + -0.05452765 5.4287076 5.0849075 -6.690375 -1.6183422 + 3.654291 0.94352573 -9.200294 -5.4749465 -3.5235846 + 1.3420814 4.240421 -2.772944 -2.8451524 16.311104 + 4.2969875 -1.762936 -12.5758915 8.595198 -0.8835239 + -1.5708797 1.568961 1.1413603 3.5032008 -0.45251232 + -6.786333 16.89443 5.3366146 -8.789056 0.6355629 + 3.2579517 -3.328322 7.5969577 0.66025066 -6.550468 + -9.148656 2.020372 -0.4615173 1.1965656 -3.8764873 + 11.6562195 -6.0750933 12.182899 3.2218833 0.81969476 + 5.570001 -3.8459578 -7.205299 7.9262037 -7.6611166 + -5.249467 -2.2671914 7.2658715 -13.298164 4.821147 + -2.7263982 11.691089 -3.8918593 -2.838112 -1.0336838 + -3.8034165 2.8536487 -5.60398 -1.1972581 1.3455094 + -3.4903061 2.2408795 5.5010734 -3.970756 11.99696 + -7.8858757 0.43160373 -5.5059714 4.3426995 16.322706 + 11.635366 0.72157705 -9.245714 -3.91465 -4.449838 + -1.5716927 7.713747 -2.2430465 -6.198303 -13.481864 + 2.8156567 -5.7812386 5.1456156 2.7289324 -14.505571 + 13.270688 3.448231 -7.0659585 4.5886116 -4.466099 + -0.296428 -11.463529 -2.6076477 14.110243 -6.9725137 + -1.9962958 2.7119343 19.391657 0.01961198 14.607133 + -1.6695905 -4.391516 1.3131028 -6.670972 -5.888604 + 12.0612335 5.9285784 3.3715196 1.492534 10.723728 + -0.95514804 -12.085431 ] # get the score between enroll and test - Eembeddings Score: 0.3965281546115875 + Eembeddings Score: 0.4292638301849365 ``` ### 4.预训练模型 diff --git a/examples/voxceleb/sv0/RESULT.md b/examples/voxceleb/sv0/RESULT.md index c37bcece..fcf5a7b3 100644 --- a/examples/voxceleb/sv0/RESULT.md +++ b/examples/voxceleb/sv0/RESULT.md @@ -4,4 +4,4 @@ | Model | Number of Params | Release | Config | dim | Test set | Cosine | Cosine + S-Norm | | --- | --- | --- | --- | --- | --- | --- | ---- | -| ECAPA-TDNN | 85M | 0.1.1 | conf/ecapa_tdnn.yaml |192 | test | 1.15 | 1.06 | +| ECAPA-TDNN | 85M | 0.1.2 | conf/ecapa_tdnn.yaml |192 | test | 1.02 | 0.95 | diff --git a/paddlespeech/cli/vector/infer.py b/paddlespeech/cli/vector/infer.py index f709383d..9904b5ed 100644 --- a/paddlespeech/cli/vector/infer.py +++ b/paddlespeech/cli/vector/infer.py @@ -43,9 +43,9 @@ pretrained_models = { # "paddlespeech vector --task spk --model ecapatdnn_voxceleb12-16k --sr 16000 --input ./input.wav" "ecapatdnn_voxceleb12-16k": { 'url': - 'https://paddlespeech.bj.bcebos.com/vector/voxceleb/sv0_ecapa_tdnn_voxceleb12_ckpt_0_1_1.tar.gz', + 'https://paddlespeech.bj.bcebos.com/vector/voxceleb/sv0_ecapa_tdnn_voxceleb12_ckpt_0_1_2.tar.gz', 'md5': - 'a1c0dba7d4de997187786ff517d5b4ec', + 'cc33023c54ab346cd318408f43fcaf95', 'cfg_path': 'conf/model.yaml', # the yaml config path 'ckpt_path': From 9b5f7f71ac0732298a526689ed5dc90b3e6f8779 Mon Sep 17 00:00:00 2001 From: xiongxinlei Date: Thu, 7 Apr 2022 18:07:28 +0800 Subject: [PATCH 4/4] add part ecapa-tdnn note, test=doc --- demos/speaker_verification/README.md | 2 ++ demos/speaker_verification/README_cn.md | 2 ++ paddlespeech/vector/models/ecapa_tdnn.py | 46 ++++++++++++++++++++++++ 3 files changed, 50 insertions(+) diff --git a/demos/speaker_verification/README.md b/demos/speaker_verification/README.md index 27413bd8..7d7180ae 100644 --- a/demos/speaker_verification/README.md +++ b/demos/speaker_verification/README.md @@ -117,6 +117,8 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav audio_file='./123456789.wav', device=paddle.get_device()) print('Test embedding Result: \n{}'.format(test_emb)) + + # score range [0, 1] score = vector_executor.get_embeddings_score(audio_emb, test_emb) print(f"Eembeddings Score: {score}") ``` diff --git a/demos/speaker_verification/README_cn.md b/demos/speaker_verification/README_cn.md index 068802fd..db382f29 100644 --- a/demos/speaker_verification/README_cn.md +++ b/demos/speaker_verification/README_cn.md @@ -115,6 +115,8 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav audio_file='./123456789.wav', device=paddle.get_device()) print('Test embedding Result: \n{}'.format(test_emb)) + + # score range [0, 1] score = vector_executor.get_embeddings_score(audio_emb, test_emb) print(f"Eembeddings Score: {score}") ``` diff --git a/paddlespeech/vector/models/ecapa_tdnn.py b/paddlespeech/vector/models/ecapa_tdnn.py index 0e7287cd..895ff13f 100644 --- a/paddlespeech/vector/models/ecapa_tdnn.py +++ b/paddlespeech/vector/models/ecapa_tdnn.py @@ -79,6 +79,20 @@ class Conv1d(nn.Layer): bias_attr=bias, ) def forward(self, x): + """Do conv1d forward + + Args: + x (paddle.Tensor): [N, C, L] input data, + N is the batch, + C is the data dimension, + L is the time + + Raises: + ValueError: only support the same padding type + + Returns: + paddle.Tensor: the value of conv1d + """ if self.padding == "same": x = self._manage_padding(x, self.kernel_size, self.dilation, self.stride) @@ -88,6 +102,20 @@ class Conv1d(nn.Layer): return self.conv(x) def _manage_padding(self, x, kernel_size: int, dilation: int, stride: int): + """Padding the input data + + Args: + x (paddle.Tensor): [N, C, L] input data + N is the batch, + C is the data dimension, + L is the time + kernel_size (int): 1-d convolution kernel size + dilation (int): 1-d convolution dilation + stride (int): 1-d convolution stride + + Returns: + paddle.Tensor: the padded input data + """ L_in = x.shape[-1] # Detecting input shape padding = self._get_padding_elem(L_in, stride, kernel_size, dilation) # Time padding @@ -101,6 +129,17 @@ class Conv1d(nn.Layer): stride: int, kernel_size: int, dilation: int): + """Calculate the padding value in same mode + + Args: + L_in (int): the times of the input data, + stride (int): 1-d convolution stride + kernel_size (int): 1-d convolution kernel size + dilation (int): 1-d convolution stride + + Returns: + int: return the padding value in same mode + """ if stride > 1: n_steps = math.ceil(((L_in - kernel_size * dilation) / stride) + 1) L_out = stride * (n_steps - 1) + kernel_size * dilation @@ -245,6 +284,13 @@ class SEBlock(nn.Layer): class AttentiveStatisticsPooling(nn.Layer): def __init__(self, channels, attention_channels=128, global_context=True): + """Compute the speaker verification statistics + The detail info is section 3.1 in https://arxiv.org/pdf/1709.01507.pdf + Args: + channels (int): input data channel or data dimension + attention_channels (int, optional): attention dimension. Defaults to 128. + global_context (bool, optional): If use the global context information. Defaults to True. + """ super().__init__() self.eps = 1e-12