Duplicate from JSWOOK/pyannote_3_fine_tuning

Co-authored-by: Jeon Sang Wook <JSWOOK@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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
+*.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
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+language:
+- en
+license: mit
+base_model: pyannote/speaker-diarization-3.1
+tags:
+- speaker-diarization
+- speaker-segmentation
+- generated_from_trainer
+datasets:
+- diarizers-community/voxconverse
+model-index:
+- name: JSWOOK/pyannote_3_fine_tuning
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# JSWOOK/pyannote_3_fine_tuning
+
+This model is a fine-tuned version of [pyannote/speaker-diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1) on the diarizers-community/voxconverse dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3134
+- Model Preparation Time: 0.0048
+- Der: 0.0888
+- False Alarm: 0.0134
+- Missed Detection: 0.0337
+- Confusion: 0.0417
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der    | False Alarm | Missed Detection | Confusion |
+|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:-----------:|:----------------:|:---------:|
+| No log        | 1.0   | 24   | 0.3180          | 0.0048                 | 0.0915 | 0.0119      | 0.0385           | 0.0410    |
+| 0.1903        | 2.0   | 48   | 0.3116          | 0.0048                 | 0.0903 | 0.0125      | 0.0369           | 0.0409    |
+| 0.1839        | 3.0   | 72   | 0.3089          | 0.0048                 | 0.0896 | 0.0128      | 0.0357           | 0.0411    |
+| 0.1825        | 4.0   | 96   | 0.3176          | 0.0048                 | 0.0896 | 0.0131      | 0.0352           | 0.0413    |
+| 0.1797        | 5.0   | 120  | 0.3148          | 0.0048                 | 0.0892 | 0.0132      | 0.0346           | 0.0413    |
+| 0.1801        | 6.0   | 144  | 0.3141          | 0.0048                 | 0.0890 | 0.0133      | 0.0342           | 0.0415    |
+| 0.1735        | 7.0   | 168  | 0.3137          | 0.0048                 | 0.0887 | 0.0134      | 0.0338           | 0.0416    |
+| 0.1705        | 8.0   | 192  | 0.3133          | 0.0048                 | 0.0887 | 0.0134      | 0.0337           | 0.0416    |
+| 0.1796        | 9.0   | 216  | 0.3133          | 0.0048                 | 0.0887 | 0.0134      | 0.0337           | 0.0417    |
+| 0.1644        | 10.0  | 240  | 0.3134          | 0.0048                 | 0.0888 | 0.0134      | 0.0337           | 0.0417    |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,18 @@
+{
+  "architectures": [
+    "SegmentationModel"
+  ],
+  "chunk_duration": 10.0,
+  "max_speakers_per_chunk": 3,
+  "max_speakers_per_frame": 2,
+  "min_duration": null,
+  "model_type": "pyannet",
+  "sample_rate": 16000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "warm_up": [
+    0.0,
+    0.0
+  ],
+  "weigh_by_cardinality": false
+}

config.yaml

@@ -0,0 +1,19 @@
+version: 3.0.0
+
+pipeline:
+  name: pyannote.audio.pipelines.SpeakerDiarization
+  params:
+    clustering: AgglomerativeClustering
+    embedding: hbredin/wespeaker-voxceleb-resnet34-LM
+    embedding_batch_size: 16
+    embedding_exclude_overlap: true
+    segmentation: pyannote/segmentation-3.0
+    segmentation_batch_size: 32
+
+params:
+  clustering:
+    method: centroid
+    min_cluster_size: 12
+    threshold: 0.7045654963945799
+  segmentation:
+    min_duration_off: 0.0

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0851ed0984dbbc22a62ba602a1cc18eeb3fbbf2a1deb515812f41056a04b9303
+size 5899124

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:511ceac6e3c008f19fbe4b6b944cada16c75921dc5b1f3d4d2cc01ebc87b0206
+size 5905907

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:677f6b93b8287b812971afc0a22f66d80d0d008b82848cf17084db5a42d37f5f
+size 5240