Model save

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: openai/whisper-tiny.en
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: multiclass-fz-enc-tiny-en
+  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. -->
+
+# multiclass-fz-enc-tiny-en
+
+This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1596
+- Wer: 21.1301
+- Cer: 17.7602
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 5000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Wer      | Cer      |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:--------:|
+| 0.1904        | 4.5872  | 500  | 0.3362          | 519.8481 | 547.0715 |
+| 0.014         | 9.1743  | 1000 | 0.1819          | 17.2365  | 18.1553  |
+| 0.0017        | 13.7615 | 1500 | 0.1720          | 12.1083  | 7.9955   |
+| 0.0008        | 18.3486 | 2000 | 0.1668          | 12.3932  | 11.7657  |
+| 0.0005        | 22.9358 | 2500 | 0.1640          | 12.2032  | 11.8430  |
+| 0.0004        | 27.5229 | 3000 | 0.1622          | 11.9658  | 11.7056  |
+| 0.0003        | 32.1101 | 3500 | 0.1615          | 11.8234  | 7.7808   |
+| 0.0003        | 36.6972 | 4000 | 0.1605          | 21.3675  | 17.9320  |
+| 0.0002        | 41.2844 | 4500 | 0.1596          | 21.1301  | 17.7602  |
+| 0.0002        | 45.8716 | 5000 | 0.1596          | 21.1301  | 17.7602  |
+
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.0

generation_config.json

@@ -0,0 +1,58 @@
+{
+  "alignment_heads": [
+    [
+      1,
+      0
+    ],
+    [
+      2,
+      0
+    ],
+    [
+      2,
+      5
+    ],
+    [
+      3,
+      0
+    ],
+    [
+      3,
+      1
+    ],
+    [
+      3,
+      2
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50257,
+  "eos_token_id": 50256,
+  "forced_decoder_ids": [
+    [
+      1,
+      50362
+    ]
+  ],
+  "is_multilingual": false,
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50362,
+  "pad_token_id": 50256,
+  "prev_sot_token_id": 50360,
+  "return_timestamps": false,
+  "suppress_tokens": [],
+  "transformers_version": "4.45.1"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1033a3b0516d2454d1c41bed59e320629851b0aaa503b02c131fc323a3b4c5c4
+oid sha256:f273b1eb770867055968725404145a816ab901747df2021dd3faad242b728b5e
 size 151060136

runs/Oct01_16-33-01_iros02-pod/events.out.tfevents.1727800383.iros02-pod.84636.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a4c487c296832089d21fbe54b7023d597c73b4b85d2104ecba9ec55504533eb
-size 46413
+oid sha256:98e1722f205b80d2f9fe65fd78a177d80437db43b3d65f3796d76efa63408c88
+size 46624