Added a model file

Browse files

Files changed (17) hide show

.gitattributes +3 -9
README.md +131 -0
config.yaml +20 -0
reproducible_research/2022.07/AISHELL.SpeakerDiarization.Full.test.eval +24 -0
reproducible_research/2022.07/AISHELL.SpeakerDiarization.Full.test.rttm +0 -0
reproducible_research/2022.07/AMI-SDM.SpeakerDiarization.only_words.test.eval +20 -0
reproducible_research/2022.07/AMI-SDM.SpeakerDiarization.only_words.test.rttm +0 -0
reproducible_research/2022.07/AMI.SpeakerDiarization.only_words.test.eval +20 -0
reproducible_research/2022.07/AMI.SpeakerDiarization.only_words.test.rttm +0 -0
reproducible_research/2022.07/CALLHOME.SpeakerDiarization.CALLHOME.test.eval +254 -0
reproducible_research/2022.07/CALLHOME.SpeakerDiarization.CALLHOME.test.rttm +0 -0
reproducible_research/2022.07/DIHARD.SpeakerDiarization.Full.test.eval +263 -0
reproducible_research/2022.07/DIHARD.SpeakerDiarization.Full.test.rttm +0 -0
reproducible_research/2022.07/REPERE.SpeakerDiarization.Full.test.eval +65 -0
reproducible_research/2022.07/REPERE.SpeakerDiarization.Full.test.rttm +0 -0
reproducible_research/2022.07/VoxConverse.SpeakerDiarization.VoxConverse.test.eval +236 -0
reproducible_research/2022.07/VoxConverse.SpeakerDiarization.VoxConverse.test.rttm +0 -0

.gitattributes CHANGED Viewed

@@ -1,33 +1,27 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -1,3 +1,134 @@
 ---
 license: mit
 ---

 ---
+tags:
+- pyannote
+- pyannote-audio
+- pyannote-audio-pipeline
+- audio
+- voice
+- speech
+- speaker
+- speaker-diarization
+- speaker-change-detection
+- voice-activity-detection
+- overlapped-speech-detection
+- automatic-speech-recognition
+datasets:
+- ami
+- dihard
+- voxconverse
+- aishell
+- repere
+- voxceleb
 license: mit
+extra_gated_prompt: "The collected information will help acquire a better knowledge of pyannote.audio userbase and help its maintainers apply for grants to improve it further. If you are an academic researcher, please cite the relevant papers in your own publications using the model. If you work for a company, please consider contributing back to pyannote.audio development (e.g. through unrestricted gifts). We also provide scientific consulting services around speaker diarization and machine listening."
+extra_gated_fields:
+  Company/university: text
+  Website: text
+  I plan to use this model for (task, type of audio data, etc): text
 ---
+# 🎹 Speaker diarization
+Relies on pyannote.audio 2.0.1: see [installation instructions](https://github.com/pyannote/pyannote-audio#installation).
+## TL;DR
+```python
+# load the pipeline from Hugginface Hub
+from pyannote.audio import Pipeline
+pipeline = Pipeline.from_pretrained("pyannote/[email protected]")
+# apply the pipeline to an audio file
+diarization = pipeline("audio.wav")
+# dump the diarization output to disk using RTTM format
+with open("audio.rttm", "w") as rttm:
+    diarization.write_rttm(rttm)
+```
+## Advanced usage
+In case the number of speakers is known in advance, one can use the `num_speakers` option:
+```python
+diarization = pipeline("audio.wav", num_speakers=2)
+```
+One can also provide lower and/or upper bounds on the number of speakers using `min_speakers` and `max_speakers` options:
+```python
+diarization = pipeline("audio.wav", min_speakers=2, max_speakers=5)
+```
+If you feel adventurous, you can try and play with the various pipeline hyper-parameters.
+For instance, one can use a more aggressive voice activity detection by increasing the value of `segmentation_onset` threshold:
+```python
+hparams = pipeline.parameters(instantiated=True)
+hparams["segmentation_onset"] += 0.1
+pipeline.instantiate(hparams)
+```
+## Benchmark
+### Real-time factor
+Real-time factor is around 5% using one Nvidia Tesla V100 SXM2 GPU (for the neural inference part) and one Intel Cascade Lake 6248 CPU (for the clustering part).
+In other words, it takes approximately 3 minutes to process a one hour conversation.
+### Accuracy
+This pipeline is benchmarked on a growing collection of datasets.
+Processing is fully automatic:
+* no manual voice activity detection (as is sometimes the case in the literature)
+* no manual number of speakers (though it is possible to provide it to the pipeline)
+* no fine-tuning of the internal models nor tuning of the pipeline hyper-parameters to each dataset
+... with the least forgiving diarization error rate (DER) setup (named *"Full"* in [this paper](https://doi.org/10.1016/j.csl.2021.101254)):
+* no forgiveness collar
+* evaluation of overlapped speech
+| Benchmark (2.0.1)                                                                                                                  | [DER%](. "Diarization error rate") | [FA%](. "False alarm rate") | [Miss%](. "Missed detection rate") | [Conf%](. "Speaker confusion rate") | Expected output                                                                                                                                          | File-level evaluation                                                                                                                                    |
+| ---------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------- | --------------------------- | ---------------------------------- | ----------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| [AISHELL-4](http://www.openslr.org/111/)                                                                                           | 14.61                              | 3.31                        | 4.35                               | 6.95                                | [RTTM](https://huggingface.co/pyannote/speaker-diarization/blob/2022.07/reproducible_research/2022.07/AISHELL.SpeakerDiarization.Full.test.rttm)         | [eval](https://huggingface.co/pyannote/speaker-diarization/blob/2022.07/reproducible_research/2022.07/AISHELL.SpeakerDiarization.Full.test.eval)         |
+| [AMI *Mix-Headset*](https://groups.inf.ed.ac.uk/ami/corpus/) [*only_words*](https://github.com/BUTSpeechFIT/AMI-diarization-setup) | 18.21                              | 3.28                        | 11.07                              | 3.87                                | [RTTM](https://huggingface.co/pyannote/speaker-diarization/blob/2022.07/reproducible_research/2022.07/AMI.SpeakerDiarization.only_words.test.rttm)       | [eval](https://huggingface.co/pyannote/speaker-diarization/blob/2022.07/reproducible_research/2022.07/AMI.SpeakerDiarization.only_words.test.eval)       |
+| [AMI *Array1-01*](https://groups.inf.ed.ac.uk/ami/corpus/) [*only_words*](https://github.com/BUTSpeechFIT/AMI-diarization-setup)   | 29.00                              | 2.71                        | 21.61                              | 4.68                                | [RTTM](https://huggingface.co/pyannote/speaker-diarization/blob/2022.07/reproducible_research/2022.07/AMI-SDM.SpeakerDiarization.only_words.test.rttm)   | [eval](https://huggingface.co/pyannote/speaker-diarization/blob/2022.07/reproducible_research/2022.07/AMI-SDM.SpeakerDiarization.only_words.test.eval)   |
+| [CALLHOME](https://catalog.ldc.upenn.edu/LDC2001S97) [*Part2*](https://github.com/BUTSpeechFIT/CALLHOME_sublists/issues/1)         | 30.24                              | 3.71                        | 16.86                              | 9.66                                | [RTTM](https://huggingface.co/pyannote/speaker-diarization/blob/2022.07/reproducible_research/2022.07/CALLHOME.SpeakerDiarization.CALLHOME.test.rttm)    | [eval](https://huggingface.co/pyannote/speaker-diarization/blob/2022.07/reproducible_research/2022.07/CALLHOME.SpeakerDiarization.CALLHOME.test.eval)    |
+| [DIHARD 3 *Full*](https://arxiv.org/abs/2012.01477)                                                                                | 20.99                              | 4.25                        | 10.74                              | 6.00                                | [RTTM](https://huggingface.co/pyannote/speaker-diarization/blob/2022.07/reproducible_research/2022.07/DIHARD.SpeakerDiarization.Full.test.rttm)          | [eval](https://huggingface.co/pyannote/speaker-diarization/blob/2022.07/reproducible_research/2022.07/DIHARD.SpeakerDiarization.Full.test.eval)          |
+| [REPERE *Phase 2*](https://islrn.org/resources/360-758-359-485-0/)                                                                 | 12.62                              | 1.55                        | 3.30                               | 7.76                                | [RTTM](https://huggingface.co/pyannote/speaker-diarization/blob/2022.07/reproducible_research/2022.07/REPERE.SpeakerDiarization.Full.test.rttm)          | [eval](https://huggingface.co/pyannote/speaker-diarization/blob/2022.07/reproducible_research/2022.07/REPERE.SpeakerDiarization.Full.test.eval)          |
+| [VoxConverse *v0.3*](https://github.com/joonson/voxconverse)                                                                       | 12.61                              | 3.45                        | 3.85                               | 5.31                                | [RTTM](https://huggingface.co/pyannote/speaker-diarization/blob/main/reproducible_research/2022.07/VoxConverse.SpeakerDiarization.VoxConverse.test.rttm) | [eval](https://huggingface.co/pyannote/speaker-diarization/blob/main/reproducible_research/2022.07/VoxConverse.SpeakerDiarization.VoxConverse.test.eval) |
+## Support
+For commercial enquiries and scientific consulting, please contact [me](mailto:[email protected]).
+For [technical questions](https://github.com/pyannote/pyannote-audio/discussions) and [bug reports](https://github.com/pyannote/pyannote-audio/issues), please check [pyannote.audio](https://github.com/pyannote/pyannote-audio) Github repository.
+## Citations
+```bibtex
+@inproceedings{Bredin2021,
+  Title = {{End-to-end speaker segmentation for overlap-aware resegmentation}},
+  Author = {{Bredin}, Herv{\'e} and {Laurent}, Antoine},
+  Booktitle = {Proc. Interspeech 2021},
+  Address = {Brno, Czech Republic},
+  Month = {August},
+  Year = {2021},
+}
+```
+```bibtex
+@inproceedings{Bredin2020,
+  Title = {{pyannote.audio: neural building blocks for speaker diarization}},
+  Author = {{Bredin}, Herv{\'e} and {Yin}, Ruiqing and {Coria}, Juan Manuel and {Gelly}, Gregory and {Korshunov}, Pavel and {Lavechin}, Marvin and {Fustes}, Diego and {Titeux}, Hadrien and {Bouaziz}, Wassim and {Gill}, Marie-Philippe},
+  Booktitle = {ICASSP 2020, IEEE International Conference on Acoustics, Speech, and Signal Processing},
+  Address = {Barcelona, Spain},
+  Month = {May},
+  Year = {2020},
+}
+```

config.yaml ADDED Viewed

	@@ -0,0 +1,20 @@

+pipeline:
+  name: pyannote.audio.pipelines.SpeakerDiarization
+  params:
+    segmentation: pyannote/[email protected]
+    segmentation_step: 0.1
+    segmentation_batch_size: 32
+    # embedding: speechbrain/spkrec-ecapa-voxceleb@5c0be3875fda05e81f3c004ed8c7c06be308de1e
+    embedding: speechbrain/spkrec-ecapa-voxceleb
+    embedding_exclude_overlap: True
+    embedding_batch_size: 32
+    clustering: HiddenMarkovModelClustering
+params:
+  segmentation_onset: 0.58
+  clustering:
+    covariance_type: diag
+    threshold: 0.35
+    single_cluster_detection:
+      quantile: 0.05
+      threshold: 1.15

reproducible_research/2022.07/AISHELL.SpeakerDiarization.Full.test.eval ADDED Viewed

	@@ -0,0 +1,24 @@

+             diarization error rate    total  correct correct false alarm false alarm missed detection missed detection confusion confusion
+                                  %                         %                       %                                 %                   %
+item
+L_R003S01C02                  18.89  2311.97  1980.25   85.65      104.95        4.54           144.55             6.25    187.17      8.10
+L_R003S02C02                  12.74  2036.79  1832.36   89.96       55.15        2.71            93.48             4.59    110.94      5.45
+L_R003S03C02                  16.46  2376.45  2045.30   86.07       59.97        2.52           206.09             8.67    125.06      5.26
+L_R003S04C02                  17.63  2011.85  1752.94   87.13       95.70        4.76            78.03             3.88    180.89      8.99
+L_R004S01C01                  10.96  2041.84  1877.74   91.96       59.67        2.92            53.53             2.62    110.58      5.42
+L_R004S02C01                  14.78  2204.89  1970.28   89.36       91.27        4.14            57.61             2.61    177.01      8.03
+L_R004S03C01                  12.31  2314.18  2103.86   90.91       74.52        3.22            86.45             3.74    123.87      5.35
+L_R004S06C01                   9.26  2029.95  1861.81   91.72       19.85        0.98            44.98             2.22    123.15      6.07
+M_R003S01C01                  15.04  2191.47  1935.43   88.32       73.45        3.35           126.17             5.76    129.87      5.93
+M_R003S02C01                  15.14  2376.79  2052.14   86.34       35.24        1.48           204.97             8.62    119.69      5.04
+M_R003S04C01                  37.43  2015.63  1444.81   71.68      183.54        9.11            93.33             4.63    477.50     23.69
+M_R003S05C01                  46.60  2249.68  1344.71   59.77      143.29        6.37           134.14             5.96    770.84     34.26
+S_R003S01C01                  11.02  2127.86  1984.73   93.27       91.34        4.29            69.86             3.28     73.27      3.44
+S_R003S02C01                   8.70  2222.87  2097.15   94.34       67.66        3.04            71.94             3.24     53.78      2.42
+S_R003S03C01                  10.01  2071.12  1957.05   94.49       93.19        4.50            71.56             3.45     42.51      2.05
+S_R003S04C01                  16.47  2615.78  2254.19   86.18       69.33        2.65           218.44             8.35    143.15      5.47
+S_R004S01C01                   4.65  2117.91  2043.76   96.50       24.30        1.15            64.34             3.04      9.81      0.46
+S_R004S02C01                   5.04  2095.08  2027.67   96.78       38.13        1.82            35.96             1.72     31.45      1.50
+S_R004S03C01                   2.13  2074.39  2046.66   98.66       16.48        0.79            26.72             1.29      1.01      0.05
+S_R004S04C01                   4.43  2078.85  2029.99   97.65       43.19        2.08            12.66             0.61     36.20      1.74
+TOTAL                         14.61 43565.36 38642.83   88.70     1440.22        3.31          1894.78             4.35   3027.75      6.95

reproducible_research/2022.07/AISHELL.SpeakerDiarization.Full.test.rttm ADDED Viewed