End of training

README.md

@@ -0,0 +1,91 @@
+---
+language:
+- jpn
+license: mit
+base_model: pyannote/speaker-diarization-3.1
+tags:
+- speaker-diarization
+- speaker-segmentation
+- generated_from_trainer
+datasets:
+- diarizers-community/callhome
+model-index:
+- name: speaker-segmentation-fine-tuned-callhome-jpn
+  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. -->
+
+# speaker-segmentation-fine-tuned-callhome-jpn
+
+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/callhome dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7390
+- Der: 0.2115
+- False Alarm: 0.0300
+- Missed Detection: 0.0148
+- Confusion: 0.1667
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 25
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Der    | False Alarm | Missed Detection | Confusion |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-----------:|:----------------:|:---------:|
+| 0.6055        | 1.0   | 162  | 0.7220          | 0.2327 | 0.0308      | 0.0139           | 0.1880    |
+| 0.5431        | 2.0   | 324  | 0.6852          | 0.2248 | 0.0308      | 0.0137           | 0.1803    |
+| 0.5333        | 3.0   | 486  | 0.6997          | 0.2243 | 0.0309      | 0.0137           | 0.1797    |
+| 0.4688        | 4.0   | 648  | 0.6579          | 0.2175 | 0.0309      | 0.0139           | 0.1727    |
+| 0.4674        | 5.0   | 810  | 0.6863          | 0.2206 | 0.0309      | 0.0137           | 0.1760    |
+| 0.4568        | 6.0   | 972  | 0.6751          | 0.2151 | 0.0309      | 0.0139           | 0.1703    |
+| 0.4528        | 7.0   | 1134 | 0.6515          | 0.2135 | 0.0307      | 0.0141           | 0.1686    |
+| 0.4464        | 8.0   | 1296 | 0.6786          | 0.2154 | 0.0312      | 0.0139           | 0.1704    |
+| 0.4146        | 9.0   | 1458 | 0.6735          | 0.2124 | 0.0308      | 0.0139           | 0.1677    |
+| 0.4098        | 10.0  | 1620 | 0.6900          | 0.2132 | 0.0309      | 0.0138           | 0.1686    |
+| 0.3943        | 11.0  | 1782 | 0.7008          | 0.2099 | 0.0306      | 0.0140           | 0.1653    |
+| 0.3889        | 12.0  | 1944 | 0.6992          | 0.2121 | 0.0300      | 0.0144           | 0.1676    |
+| 0.3904        | 13.0  | 2106 | 0.7262          | 0.2165 | 0.0303      | 0.0141           | 0.1720    |
+| 0.3694        | 14.0  | 2268 | 0.7131          | 0.2114 | 0.0301      | 0.0142           | 0.1671    |
+| 0.3753        | 15.0  | 2430 | 0.7101          | 0.2098 | 0.0304      | 0.0140           | 0.1654    |
+| 0.3732        | 16.0  | 2592 | 0.7181          | 0.2138 | 0.0301      | 0.0145           | 0.1692    |
+| 0.3621        | 17.0  | 2754 | 0.7293          | 0.2133 | 0.0302      | 0.0146           | 0.1684    |
+| 0.3482        | 18.0  | 2916 | 0.7399          | 0.2126 | 0.0301      | 0.0146           | 0.1679    |
+| 0.3503        | 19.0  | 3078 | 0.7351          | 0.2122 | 0.0300      | 0.0148           | 0.1673    |
+| 0.3558        | 20.0  | 3240 | 0.7367          | 0.2131 | 0.0301      | 0.0147           | 0.1682    |
+| 0.3579        | 21.0  | 3402 | 0.7437          | 0.2127 | 0.0300      | 0.0148           | 0.1679    |
+| 0.352         | 22.0  | 3564 | 0.7420          | 0.2128 | 0.0301      | 0.0148           | 0.1679    |
+| 0.3662        | 23.0  | 3726 | 0.7380          | 0.2116 | 0.0300      | 0.0148           | 0.1668    |
+| 0.3381        | 24.0  | 3888 | 0.7387          | 0.2115 | 0.0300      | 0.0148           | 0.1667    |
+| 0.3446        | 25.0  | 4050 | 0.7390          | 0.2115 | 0.0300      | 0.0148           | 0.1667    |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- 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": "4.42.4",
+  "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:ad2ad578429c58fb9f34b6c5c2905d214187c4aa22888c0f8733ba95bb82bf29
+size 5899124

runs/Sep01_18-22-43_71681bb45d1f/events.out.tfevents.1725215002.71681bb45d1f.1195.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:160f11300fc4def29ebb913dffca447a2c1a76f4eaf68bf39e623bccd2c2786a
+size 51633

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02fb8d71137c54704232868f586e715e1d5a21c5cd36b49fdfbc228cc91ca8aa
+size 5176