Model save

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: openai/whisper-base.en
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: multiclass-fz-enc-base-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-base-en
+
+This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1252
+- Wer: 16.9516
+- Cer: 6.8447
+
+## 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     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:|
+| 0.1012        | 4.5872  | 500  | 0.2309          | 21.6999 | 9.7647  |
+| 0.0068        | 9.1743  | 1000 | 0.1438          | 24.1216 | 11.7228 |
+| 0.0008        | 13.7615 | 1500 | 0.1345          | 17.5689 | 7.1453  |
+| 0.0005        | 18.3486 | 2000 | 0.1310          | 17.4264 | 7.0251  |
+| 0.0003        | 22.9358 | 2500 | 0.1286          | 17.6163 | 7.2827  |
+| 0.0002        | 27.5229 | 3000 | 0.1273          | 17.7113 | 7.2741  |
+| 0.0002        | 32.1101 | 3500 | 0.1263          | 17.0465 | 6.8963  |
+| 0.0002        | 36.6972 | 4000 | 0.1258          | 16.9516 | 6.8705  |
+| 0.0001        | 41.2844 | 4500 | 0.1253          | 16.8566 | 6.8276  |
+| 0.0001        | 45.8716 | 5000 | 0.1252          | 16.9516 | 6.8447  |
+
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.0

generation_config.json

@@ -0,0 +1,46 @@
+{
+  "alignment_heads": [
+    [
+      3,
+      3
+    ],
+    [
+      4,
+      7
+    ],
+    [
+      5,
+      1
+    ],
+    [
+      5,
+      5
+    ],
+    [
+      5,
+      7
+    ]
+  ],
+  "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 sha256:33e576cbf520410b7dc44755617719c71ec39563c26a0123274f1e69062dcf26
+oid sha256:c7e9066caaf602b5f2c80c9516d6675cac2bd8ccca376e0ff12c010c9c676ff1
 size 290401888

runs/Oct01_19-21-08_iros02-pod/events.out.tfevents.1727810470.iros02-pod.86185.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba846b028f719b1b7915ab10bfbec8299d0663334fac08ba0658c7b547af246e
-size 35555
+oid sha256:6b6734d7f337ea81f3fafdcc3b27a17cece91f82dce9555f2fbe3fa9ae642117
+size 35766