Merge pull request #1614 from Honei/vox12

[vec]change the vector output to numpy.array
PaddlePaddle · Mar 28, 2022 · d60856b · d60856b
2 parents f9bf260 + ed7113f
commit d60856b
Show file tree

Hide file tree

Showing 16 changed files with 211 additions and 256 deletions.
diff --git a/dataset/voxceleb/voxceleb1.py b/dataset/voxceleb/voxceleb1.py
@@ -63,13 +63,15 @@
 
 TRIAL_BASE_URL = "https://www.robots.ox.ac.uk/~vgg/data/voxceleb/meta/"
 TRIAL_LIST = {
-    "veri_test.txt": "29fc7cc1c5d59f0816dc15d6e8be60f7",             # voxceleb1
-    "veri_test2.txt": "b73110731c9223c1461fe49cb48dddfc",            # voxceleb1(cleaned)
-    "list_test_hard.txt": "21c341b6b2168eea2634df0fb4b8fff1",        # voxceleb1-H
-    "list_test_hard2.txt": "857790e09d579a68eb2e339a090343c8",       # voxceleb1-H(cleaned)
-    "list_test_all.txt": "b9ecf7aa49d4b656aa927a8092844e4a",         # voxceleb1-E
-    "list_test_all2.txt": "a53e059deb562ffcfc092bf5d90d9f3a"         # voxceleb1-E(cleaned)
-    }
+    "veri_test.txt": "29fc7cc1c5d59f0816dc15d6e8be60f7",  # voxceleb1
+    "veri_test2.txt": "b73110731c9223c1461fe49cb48dddfc",  # voxceleb1(cleaned)
+    "list_test_hard.txt": "21c341b6b2168eea2634df0fb4b8fff1",  # voxceleb1-H
+    "list_test_hard2.txt":
+    "857790e09d579a68eb2e339a090343c8",  # voxceleb1-H(cleaned)
+    "list_test_all.txt": "b9ecf7aa49d4b656aa927a8092844e4a",  # voxceleb1-E
+    "list_test_all2.txt":
+    "a53e059deb562ffcfc092bf5d90d9f3a"  # voxceleb1-E(cleaned)
+}
 
 parser = argparse.ArgumentParser(description=__doc__)
 parser.add_argument(
@@ -176,6 +178,7 @@ def prepare_dataset(base_url, data_list, target_dir, manifest_path,
     # create the manifest file
     create_manifest(data_dir=target_dir, manifest_path_prefix=manifest_path)
 
+
 def prepare_trial(base_url, data_list, target_dir):
     if not os.path.exists(target_dir):
         os.makedirs(target_dir)
@@ -185,10 +188,12 @@ def prepare_trial(base_url, data_list, target_dir):
         if not os.path.exists(os.path.join(target_dir, trial)):
             download_url = " --no-check-certificate " + base_url + "/" + trial
             download(url=download_url, md5sum=md5sum, target_dir=target_dir)
+
+
 def main():
     if args.target_dir.startswith('~'):
         args.target_dir = os.path.expanduser(args.target_dir)
-    
+
     # prepare the vox1 dev data
     prepare_dataset(
         base_url=BASE_URL,
@@ -209,8 +214,7 @@ def main():
     prepare_trial(
         base_url=TRIAL_BASE_URL,
         data_list=TRIAL_LIST,
-        target_dir=os.path.dirname(args.manifest_prefix)
-    )
+        target_dir=os.path.dirname(args.manifest_prefix))
 
     print("Manifest prepare done!")
 

diff --git a/dataset/voxceleb/voxceleb2.py b/dataset/voxceleb/voxceleb2.py
@@ -22,12 +22,10 @@
 import glob
 import json
 import os
-import subprocess
 from pathlib import Path
 
 import soundfile
 
-from utils.utility import check_md5sum
 from utils.utility import download
 from utils.utility import unzip
 
@@ -40,9 +38,8 @@
 DEV_DATA_URL = BASE_URL + '/vox2_aac.zip'
 DEV_MD5SUM = "bbc063c46078a602ca71605645c2a402"
 
-
 # test data
-TEST_DATA_URL = BASE_URL +  '/vox2_test_aac.zip'
+TEST_DATA_URL = BASE_URL + '/vox2_test_aac.zip'
 TEST_MD5SUM = "0d2b3ea430a821c33263b5ea37ede312"
 
 parser = argparse.ArgumentParser(description=__doc__)
@@ -56,14 +53,16 @@
     default="manifest",
     type=str,
     help="Filepath prefix for output manifests. (default: %(default)s)")
-parser.add_argument("--download", 
-                    default=False, 
-                    action="store_true", 
-                    help="Download the voxceleb2 dataset. (default: %(default)s)")
-parser.add_argument("--generate", 
-                    default=False, 
-                    action="store_true", 
-                    help="Generate the manifest files. (default: %(default)s)")
+parser.add_argument(
+    "--download",
+    default=False,
+    action="store_true",
+    help="Download the voxceleb2 dataset. (default: %(default)s)")
+parser.add_argument(
+    "--generate",
+    default=False,
+    action="store_true",
+    help="Generate the manifest files. (default: %(default)s)")
 
 args = parser.parse_args()
 
@@ -138,7 +137,7 @@ def download_dataset(url, md5sum, target_dir, dataset):
 def main():
     if args.target_dir.startswith('~'):
         args.target_dir = os.path.expanduser(args.target_dir)
-    
+
     # download and unpack the vox2-dev data
     print("download: {}".format(args.download))
     if args.download:
@@ -157,7 +156,9 @@ def main():
         print("VoxCeleb2 download is done!")
 
     if args.generate:
-        create_manifest(args.target_dir, manifest_path_prefix=args.manifest_prefix)
+        create_manifest(
+            args.target_dir, manifest_path_prefix=args.manifest_prefix)
+
 
 if __name__ == '__main__':
     main()
diff --git a/demos/audio_searching/src/operations/load.py b/demos/audio_searching/src/operations/load.py
@@ -26,8 +26,9 @@ def get_audios(path):
     """
     supported_formats = [".wav", ".mp3", ".ogg", ".flac", ".m4a"]
     return [
-        item for sublist in [[os.path.join(dir, file) for file in files]
-                             for dir, _, files in list(os.walk(path))]
+        item
+        for sublist in [[os.path.join(dir, file) for file in files]
+                        for dir, _, files in list(os.walk(path))]
         for item in sublist if os.path.splitext(item)[1] in supported_formats
     ]
 

diff --git a/demos/speaker_verification/README.md b/demos/speaker_verification/README.md
@@ -46,56 +46,46 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav
 
   Output:
 
-```bash
-  demo  {'dim': 192, 'embedding': array([ -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  ],
-      dtype=float32)}
+  ```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  ]
   ```
 
 - Python API
@@ -118,55 +108,45 @@ wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav
   Output:
   ```bash
   # Vector Result:
-   {'dim': 192, 'embedding': array([ -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  ],
-      dtype=float32)}
+   [ -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  ]
   ```
 
 ### 4.Pretrained Models