Training in progress, epoch 1

README.md

@@ -0,0 +1,86 @@
+---
+library_name: transformers
+license: mit
+base_model: pyannote/segmentation-3.0
+tags:
+- speaker-diarization
+- speaker-segmentation
+- generated_from_trainer
+datasets:
+- amityco/sample-voice-12-records
+model-index:
+- name: amity-voice-segmentation-01
+  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. -->
+
+# amity-voice-segmentation-01
+
+This model is a fine-tuned version of [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segmentation-3.0) on the amityco/sample-voice-12-records dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2769
+- Model Preparation Time: 0.0024
+- Der: 0.1131
+- False Alarm: 0.0455
+- Missed Detection: 0.0521
+- Confusion: 0.0155
+
+## 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: 8.5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- 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: 20.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der    | False Alarm | Missed Detection | Confusion |
+|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:-----------:|:----------------:|:---------:|
+| 0.3829        | 1.0   | 53   | 0.2804          | 0.0024                 | 0.1144 | 0.0395      | 0.0592           | 0.0157    |
+| 0.3593        | 2.0   | 106  | 0.2758          | 0.0024                 | 0.1128 | 0.0428      | 0.0544           | 0.0157    |
+| 0.36          | 3.0   | 159  | 0.2754          | 0.0024                 | 0.1170 | 0.0460      | 0.0553           | 0.0157    |
+| 0.3262        | 4.0   | 212  | 0.2773          | 0.0024                 | 0.1163 | 0.0457      | 0.0550           | 0.0157    |
+| 0.3104        | 5.0   | 265  | 0.2793          | 0.0024                 | 0.1157 | 0.0453      | 0.0547           | 0.0157    |
+| 0.3069        | 6.0   | 318  | 0.2803          | 0.0024                 | 0.1157 | 0.0462      | 0.0539           | 0.0157    |
+| 0.3077        | 7.0   | 371  | 0.2786          | 0.0024                 | 0.1154 | 0.0460      | 0.0537           | 0.0157    |
+| 0.3188        | 8.0   | 424  | 0.2747          | 0.0024                 | 0.1147 | 0.0462      | 0.0529           | 0.0157    |
+| 0.3389        | 9.0   | 477  | 0.2751          | 0.0024                 | 0.1138 | 0.0462      | 0.0521           | 0.0155    |
+| 0.3336        | 10.0  | 530  | 0.2747          | 0.0024                 | 0.1138 | 0.0463      | 0.0520           | 0.0155    |
+| 0.2899        | 11.0  | 583  | 0.2753          | 0.0024                 | 0.1134 | 0.0460      | 0.0520           | 0.0155    |
+| 0.2899        | 12.0  | 636  | 0.2765          | 0.0024                 | 0.1134 | 0.0457      | 0.0523           | 0.0155    |
+| 0.2564        | 13.0  | 689  | 0.2765          | 0.0024                 | 0.1131 | 0.0455      | 0.0521           | 0.0155    |
+| 0.3199        | 14.0  | 742  | 0.2769          | 0.0024                 | 0.1130 | 0.0453      | 0.0521           | 0.0155    |
+| 0.2743        | 15.0  | 795  | 0.2768          | 0.0024                 | 0.1131 | 0.0455      | 0.0521           | 0.0155    |
+| 0.27          | 16.0  | 848  | 0.2769          | 0.0024                 | 0.1131 | 0.0455      | 0.0521           | 0.0155    |
+| 0.3088        | 17.0  | 901  | 0.2769          | 0.0024                 | 0.1131 | 0.0455      | 0.0521           | 0.0155    |
+| 0.2941        | 18.0  | 954  | 0.2769          | 0.0024                 | 0.1131 | 0.0455      | 0.0521           | 0.0155    |
+| 0.262         | 19.0  | 1007 | 0.2769          | 0.0024                 | 0.1131 | 0.0455      | 0.0521           | 0.0155    |
+| 0.2831        | 20.0  | 1060 | 0.2769          | 0.0024                 | 0.1131 | 0.0455      | 0.0521           | 0.0155    |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

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": "4.51.3",
+  "warm_up": [
+    0.0,
+    0.0
+  ],
+  "weigh_by_cardinality": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b71db342aeb3c24417ecd720dfb80f0a6fbd91648a2db95541a7823a59c121
+size 5899124

runs/Apr23_12-09-46_b36a8ccc1898/events.out.tfevents.1745410197.b36a8ccc1898

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c832e2883320627133e09c74f7d4544dfce32dc941b6e0ddb441a6d03fb9a911
+size 27636

runs/Apr23_12-13-16_b36a8ccc1898/events.out.tfevents.1745410406.b36a8ccc1898

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a69daee9c6acf6f935ad3d972479e1966c1a1c4f23a61868895ce12edac892a7
+size 21779

runs/Apr23_12-14-45_b36a8ccc1898/events.out.tfevents.1745410492.b36a8ccc1898

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6849ee8b45139d16ec43f9bff3c538bab51f39072b9a93da69995490e2b0d72
+size 5516

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e753d3f0f1e70f8f84db38afd2ef94f0e5429ea2732e7272b44ffad6528d1b9
+size 5368