Hugging Face's logo

argmaxinc
/
speakerkit-pro

Automatic Speech Recognition
WhisperKit
Core ML
speakerkit
pyannote
diarization
speaker-diarization
whisper
asr
quantized
Model card Files Community
3
arda-argmax commited on
Commit
3d5a59e
·
verified ·
1 Parent(s): ab5bc64

Update pyannote-v3-pro speaker_embedder (#2)

Browse files

- Update pyannote-v3-pro W16A16 speaker_embedder (9c6071f8c660cb14a083f34bd0311924427b6fc9)
- Update pyannote-v3-pro W8A16 speaker_embedder (c0aba8c02aee63b54e77794284460b802ee64c29)

Files changed (17) hide show
  1. speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedder.mlmodelc/analytics/coremldata.bin +1 -1
  2. speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedder.mlmodelc/coremldata.bin +1 -1
  3. speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedder.mlmodelc/metadata.json +7 -7
  4. speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedder.mlmodelc/model.mil +0 -0
  5. speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedderPreprocessor.mlmodelc/analytics/coremldata.bin +1 -1
  6. speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedderPreprocessor.mlmodelc/coremldata.bin +1 -1
  7. speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedderPreprocessor.mlmodelc/metadata.json +3 -3
  8. speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedderPreprocessor.mlmodelc/model.mil +1 -1
  9. speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedder.mlmodelc/analytics/coremldata.bin +1 -1
  10. speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedder.mlmodelc/coremldata.bin +1 -1
  11. speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedder.mlmodelc/metadata.json +6 -6
  12. speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedder.mlmodelc/model.mil +0 -0
  13. speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedder.mlmodelc/weights/weight.bin +1 -1
  14. speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedderPreprocessor.mlmodelc/analytics/coremldata.bin +1 -1
  15. speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedderPreprocessor.mlmodelc/coremldata.bin +1 -1
  16. speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedderPreprocessor.mlmodelc/metadata.json +3 -3
  17. speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedderPreprocessor.mlmodelc/model.mil +1 -1
speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedder.mlmodelc/analytics/coremldata.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31ebd86f9f3a87ee2bb1aa32722968e3f6821d6b393171bb6b92683213f173e1
3
  size 243
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17d567af44a172e09251880ccdb8bca4431a2ebdeaf0167fb033dc5d03654c31
3
  size 243
speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedder.mlmodelc/coremldata.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bbb69d66cdb7f69a6c9d4dc1ff9b114d6097bb69581e12a706cf16e27ce10be
3
  size 370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45c627a63eb0a24cfbdb5baf7bca25b6755170841cc62c026f1522fedcdafb6
3
  size 370
speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedder.mlmodelc/metadata.json CHANGED
@@ -55,17 +55,17 @@
55
  },
56
  "userDefinedMetadata" : {
57
  "com.github.apple.coremltools.source_dialect" : "TorchScript",
58
- "com.github.apple.coremltools.version" : "8.2",
59
- "com.github.apple.coremltools.source" : "torch==2.6.0"
60
  },
61
  "inputSchema" : [
62
  {
63
  "hasShapeFlexibility" : "0",
64
  "isOptional" : "0",
65
  "dataType" : "Float16",
66
- "formattedType" : "MultiArray (Float16 1 × 998 × 80)",
67
  "shortDescription" : "",
68
- "shape" : "[1, 998, 80]",
69
  "name" : "preprocessor_output_1",
70
  "type" : "MultiArray"
71
  },
@@ -73,14 +73,14 @@
73
  "hasShapeFlexibility" : "0",
74
  "isOptional" : "0",
75
  "dataType" : "Float16",
76
- "formattedType" : "MultiArray (Float16 1 × 64 × 589)",
77
  "shortDescription" : "",
78
- "shape" : "[1, 64, 589]",
79
  "name" : "speaker_masks",
80
  "type" : "MultiArray"
81
  }
82
  ],
83
- "generatedClassName" : "SpeakerEmbedding",
84
  "method" : "predict"
85
  }
86
  ]
 
55
  },
56
  "userDefinedMetadata" : {
57
  "com.github.apple.coremltools.source_dialect" : "TorchScript",
58
+ "com.github.apple.coremltools.source" : "torch==2.5.1",
59
+ "com.github.apple.coremltools.version" : "8.1"
60
  },
61
  "inputSchema" : [
62
  {
63
  "hasShapeFlexibility" : "0",
64
  "isOptional" : "0",
65
  "dataType" : "Float16",
66
+ "formattedType" : "MultiArray (Float16 1 × 2998 × 80)",
67
  "shortDescription" : "",
68
+ "shape" : "[1, 2998, 80]",
69
  "name" : "preprocessor_output_1",
70
  "type" : "MultiArray"
71
  },
 
73
  "hasShapeFlexibility" : "0",
74
  "isOptional" : "0",
75
  "dataType" : "Float16",
76
+ "formattedType" : "MultiArray (Float16 1 × 64 × 1767)",
77
  "shortDescription" : "",
78
+ "shape" : "[1, 64, 1767]",
79
  "name" : "speaker_masks",
80
  "type" : "MultiArray"
81
  }
82
  ],
83
+ "generatedClassName" : "SpeakerEmbedder",
84
  "method" : "predict"
85
  }
86
  ]
speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedder.mlmodelc/model.mil CHANGED
The diff for this file is too large to render. See raw diff
 
speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedderPreprocessor.mlmodelc/analytics/coremldata.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1383750df1af99af002f0c3403bcf19a18c3d749706eb3498d34b0fe01abf2fc
3
  size 243
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce9bef9fb3125a5401300b5c5998c5d8f211094692cae780645d3e2757410f2c
3
  size 243
speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedderPreprocessor.mlmodelc/coremldata.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc230803421bf4fe14f843ea5b5fa0035487fd19cdd69ed670d72560b6a44586
3
  size 330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4ebd0b9ce5a84768672663aff426eb19f9648d4b9f74286f0e19fc753ad76ba
3
  size 330
speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedderPreprocessor.mlmodelc/metadata.json CHANGED
@@ -56,8 +56,8 @@
56
  },
57
  "userDefinedMetadata" : {
58
  "com.github.apple.coremltools.source_dialect" : "TorchScript",
59
- "com.github.apple.coremltools.source" : "torch==2.6.0",
60
- "com.github.apple.coremltools.version" : "8.2"
61
  },
62
  "inputSchema" : [
63
  {
@@ -71,7 +71,7 @@
71
  "type" : "MultiArray"
72
  }
73
  ],
74
- "generatedClassName" : "SpeakerEmbeddingPreprocessor",
75
  "method" : "predict"
76
  }
77
  ]
 
56
  },
57
  "userDefinedMetadata" : {
58
  "com.github.apple.coremltools.source_dialect" : "TorchScript",
59
+ "com.github.apple.coremltools.source" : "torch==2.5.1",
60
+ "com.github.apple.coremltools.version" : "8.1"
61
  },
62
  "inputSchema" : [
63
  {
 
71
  "type" : "MultiArray"
72
  }
73
  ],
74
+ "generatedClassName" : "SpeakerEmbedderPreprocessor",
75
  "method" : "predict"
76
  }
77
  ]
speaker_embedder/pyannote-v3-pro/W16A16/SpeakerEmbedderPreprocessor.mlmodelc/model.mil CHANGED
@@ -1,5 +1,5 @@
1
  program(1.0)
2
- [buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "3402.3.2"}, {"coremlc-version", "3402.4.1"}, {"coremltools-component-torch", "2.6.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "8.2"}})]
3
  {
4
  func main<ios16>(tensor<fp16, [1, 480000]> waveforms) {
5
  tensor<string, []> cast_0_dtype_0 = const()[name = tensor<string, []>("cast_0_dtype_0"), val = tensor<string, []>("fp32")];
 
1
  program(1.0)
2
+ [buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "3401.3.1"}, {"coremlc-version", "3401.4.1"}, {"coremltools-component-torch", "2.5.1"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "8.1"}})]
3
  {
4
  func main<ios16>(tensor<fp16, [1, 480000]> waveforms) {
5
  tensor<string, []> cast_0_dtype_0 = const()[name = tensor<string, []>("cast_0_dtype_0"), val = tensor<string, []>("fp32")];
speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedder.mlmodelc/analytics/coremldata.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:642e75621f11e461372ebf68c2861b4d56b48b89027295cfac05b518f88fc8f7
3
  size 243
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba8405dfc9b9348ade705e052888b4bdc7fb8d079ef3ff71108a5f692d0209f2
3
  size 243
speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedder.mlmodelc/coremldata.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bbb69d66cdb7f69a6c9d4dc1ff9b114d6097bb69581e12a706cf16e27ce10be
3
  size 370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1597d6c037ac52436b5c2e1abc47e6c68483c19eeac75267dfb8795a78ec07c5
3
  size 370
speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedder.mlmodelc/metadata.json CHANGED
@@ -56,17 +56,17 @@
56
  },
57
  "userDefinedMetadata" : {
58
  "com.github.apple.coremltools.source_dialect" : "TorchScript",
59
- "com.github.apple.coremltools.source" : "torch==2.6.0",
60
- "com.github.apple.coremltools.version" : "8.2"
61
  },
62
  "inputSchema" : [
63
  {
64
  "hasShapeFlexibility" : "0",
65
  "isOptional" : "0",
66
  "dataType" : "Float16",
67
- "formattedType" : "MultiArray (Float16 1 × 998 × 80)",
68
  "shortDescription" : "",
69
- "shape" : "[1, 998, 80]",
70
  "name" : "preprocessor_output_1",
71
  "type" : "MultiArray"
72
  },
@@ -74,9 +74,9 @@
74
  "hasShapeFlexibility" : "0",
75
  "isOptional" : "0",
76
  "dataType" : "Float16",
77
- "formattedType" : "MultiArray (Float16 1 × 64 × 589)",
78
  "shortDescription" : "",
79
- "shape" : "[1, 64, 589]",
80
  "name" : "speaker_masks",
81
  "type" : "MultiArray"
82
  }
 
56
  },
57
  "userDefinedMetadata" : {
58
  "com.github.apple.coremltools.source_dialect" : "TorchScript",
59
+ "com.github.apple.coremltools.version" : "8.2",
60
+ "com.github.apple.coremltools.source" : "torch==2.6.0"
61
  },
62
  "inputSchema" : [
63
  {
64
  "hasShapeFlexibility" : "0",
65
  "isOptional" : "0",
66
  "dataType" : "Float16",
67
+ "formattedType" : "MultiArray (Float16 1 × 2998 × 80)",
68
  "shortDescription" : "",
69
+ "shape" : "[1, 2998, 80]",
70
  "name" : "preprocessor_output_1",
71
  "type" : "MultiArray"
72
  },
 
74
  "hasShapeFlexibility" : "0",
75
  "isOptional" : "0",
76
  "dataType" : "Float16",
77
+ "formattedType" : "MultiArray (Float16 1 × 64 × 1767)",
78
  "shortDescription" : "",
79
+ "shape" : "[1, 64, 1767]",
80
  "name" : "speaker_masks",
81
  "type" : "MultiArray"
82
  }
speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedder.mlmodelc/model.mil CHANGED
The diff for this file is too large to render. See raw diff
 
speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedder.mlmodelc/weights/weight.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14c666c28766dd780a3afc3dbb4b44078e418e16f44d97780b9f8555407213a1
3
  size 6661888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a02861969f47cf3a67e3b0d276e54b3c8bc3a6e43d40d77d1cccbd57da0e5795
3
  size 6661888
speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedderPreprocessor.mlmodelc/analytics/coremldata.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1383750df1af99af002f0c3403bcf19a18c3d749706eb3498d34b0fe01abf2fc
3
  size 243
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce9bef9fb3125a5401300b5c5998c5d8f211094692cae780645d3e2757410f2c
3
  size 243
speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedderPreprocessor.mlmodelc/coremldata.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc230803421bf4fe14f843ea5b5fa0035487fd19cdd69ed670d72560b6a44586
3
  size 330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4ebd0b9ce5a84768672663aff426eb19f9648d4b9f74286f0e19fc753ad76ba
3
  size 330
speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedderPreprocessor.mlmodelc/metadata.json CHANGED
@@ -56,8 +56,8 @@
56
  },
57
  "userDefinedMetadata" : {
58
  "com.github.apple.coremltools.source_dialect" : "TorchScript",
59
- "com.github.apple.coremltools.source" : "torch==2.6.0",
60
- "com.github.apple.coremltools.version" : "8.2"
61
  },
62
  "inputSchema" : [
63
  {
@@ -71,7 +71,7 @@
71
  "type" : "MultiArray"
72
  }
73
  ],
74
- "generatedClassName" : "SpeakerEmbeddingPreprocessor",
75
  "method" : "predict"
76
  }
77
  ]
 
56
  },
57
  "userDefinedMetadata" : {
58
  "com.github.apple.coremltools.source_dialect" : "TorchScript",
59
+ "com.github.apple.coremltools.source" : "torch==2.5.1",
60
+ "com.github.apple.coremltools.version" : "8.1"
61
  },
62
  "inputSchema" : [
63
  {
 
71
  "type" : "MultiArray"
72
  }
73
  ],
74
+ "generatedClassName" : "SpeakerEmbedderPreprocessor",
75
  "method" : "predict"
76
  }
77
  ]
speaker_embedder/pyannote-v3-pro/W8A16/SpeakerEmbedderPreprocessor.mlmodelc/model.mil CHANGED
@@ -1,5 +1,5 @@
1
  program(1.0)
2
- [buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "3402.3.2"}, {"coremlc-version", "3402.4.1"}, {"coremltools-component-torch", "2.6.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "8.2"}})]
3
  {
4
  func main<ios16>(tensor<fp16, [1, 480000]> waveforms) {
5
  tensor<string, []> cast_0_dtype_0 = const()[name = tensor<string, []>("cast_0_dtype_0"), val = tensor<string, []>("fp32")];
 
1
  program(1.0)
2
+ [buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "3401.3.1"}, {"coremlc-version", "3401.4.1"}, {"coremltools-component-torch", "2.5.1"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "8.1"}})]
3
  {
4
  func main<ios16>(tensor<fp16, [1, 480000]> waveforms) {
5
  tensor<string, []> cast_0_dtype_0 = const()[name = tensor<string, []>("cast_0_dtype_0"), val = tensor<string, []>("fp32")];