Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +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
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt 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
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
 *.tar.* 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
+*.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,70 @@
----
-license: mit
----
+---
+tags:
+- pyannote
+- pyannote-audio
+- pyannote-audio-pipeline
+- audio
+- voice
+- speech
+- speaker
+- voice-activity-detection
+- automatic-speech-recognition
+datasets:
+- ami
+- dihard
+- voxconverse
+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
+---
+
+Using this open-source model in production?  
+Consider switching to [pyannoteAI](https://www.pyannote.ai) for better and faster options.
+
+# 🎹 Voice activity detection
+
+Relies on pyannote.audio 2.1: see [installation instructions](https://github.com/pyannote/pyannote-audio#installation).
+
+
+```python
+# 1. visit hf.co/pyannote/segmentation and accept user conditions
+# 2. visit hf.co/settings/tokens to create an access token
+# 3. instantiate pretrained voice activity detection pipeline
+
+from pyannote.audio import Pipeline
+pipeline = Pipeline.from_pretrained("pyannote/voice-activity-detection",
+                                    use_auth_token="ACCESS_TOKEN_GOES_HERE")
+output = pipeline("audio.wav")
+
+for speech in output.get_timeline().support():
+    # active speech between speech.start and speech.end
+    ...
+```
+
+
+## Citation
+
+```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

@@ -0,0 +1,10 @@
+pipeline:
+  name: pyannote.audio.pipelines.VoiceActivityDetection
+  params:
+    segmentation: pyannote/segmentation@Interspeech2021
+
+params:
+  min_duration_off: 0.09791355693027545
+  min_duration_on: 0.05537587440407595
+  offset: 0.4806866463041527
+  onset: 0.8104268538848918