End of training

README.md

@@ -0,0 +1,76 @@
+---
+library_name: transformers
+license: mit
+base_model: pyannote/segmentation-3.0
+tags:
+- speaker-diarization
+- speaker-segmentation
+- generated_from_trainer
+datasets:
+- abar-uwc/medical-segmentation-dataset_v2
+model-index:
+- name: medical_segmentation_v2
+  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. -->
+
+# medical_segmentation_v2
+
+This model is a fine-tuned version of [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segmentation-3.0) on the abar-uwc/medical-segmentation-dataset_v2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0143
+- Model Preparation Time: 0.004
+- Der: 0.0033
+- False Alarm: 0.0014
+- Missed Detection: 0.0017
+- Confusion: 0.0002
+
+## 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: 0.001
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der    | False Alarm | Missed Detection | Confusion |
+|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:-----------:|:----------------:|:---------:|
+| 0.0153        | 1.0   | 202  | 0.0290          | 0.004                  | 0.0067 | 0.0028      | 0.0027           | 0.0012    |
+| 0.0116        | 2.0   | 404  | 0.0192          | 0.004                  | 0.0045 | 0.0020      | 0.0021           | 0.0004    |
+| 0.0102        | 3.0   | 606  | 0.0162          | 0.004                  | 0.0037 | 0.0016      | 0.0020           | 0.0002    |
+| 0.0086        | 4.0   | 808  | 0.0165          | 0.004                  | 0.0042 | 0.0021      | 0.0019           | 0.0002    |
+| 0.0089        | 5.0   | 1010 | 0.0156          | 0.004                  | 0.0040 | 0.0018      | 0.0020           | 0.0002    |
+| 0.0059        | 6.0   | 1212 | 0.0145          | 0.004                  | 0.0035 | 0.0016      | 0.0017           | 0.0002    |
+| 0.0055        | 7.0   | 1414 | 0.0147          | 0.004                  | 0.0035 | 0.0016      | 0.0017           | 0.0002    |
+| 0.0069        | 8.0   | 1616 | 0.0142          | 0.004                  | 0.0033 | 0.0015      | 0.0017           | 0.0001    |
+| 0.0067        | 9.0   | 1818 | 0.0142          | 0.004                  | 0.0032 | 0.0014      | 0.0017           | 0.0001    |
+| 0.0063        | 10.0  | 2020 | 0.0143          | 0.004                  | 0.0033 | 0.0014      | 0.0017           | 0.0002    |
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.7.0+cu126
+- Datasets 3.5.0
+- Tokenizers 0.21.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f15af6773744b4c2c52b616008f3acb1c2c5c5f1caa82aeafabd18b5dc7309
+oid sha256:9560a292e80dccad83f39be200163f7356ec467f528a5434cc7f9c645ef03e77
 size 5899124