bigmorning's picture
Upload TFWhisperForConditionalGeneration
b7575c8
|
raw
history blame
2.12 kB
---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_keras_callback
model-index:
- name: whisper_new_split_ch_08__0005
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# whisper_new_split_ch_08__0005
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 3.0948
- Train Accuracy: 0.0343
- Train Wermet: 0.0859
- Validation Loss: 3.0780
- Validation Accuracy: 0.0341
- Validation Wermet: 0.0021
- Epoch: 4
## 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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
| 5.1494 | 0.0196 | 3.7403 | 4.3409 | 0.0256 | 0.7553 | 0 |
| 4.0236 | 0.0274 | 0.6316 | 3.6960 | 0.0302 | 0.1658 | 1 |
| 3.5216 | 0.0312 | 0.1467 | 3.3497 | 0.0311 | 0.0012 | 2 |
| 3.2259 | 0.0330 | 0.0850 | 3.1532 | 0.0337 | 0.0023 | 3 |
| 3.0948 | 0.0343 | 0.0859 | 3.0780 | 0.0341 | 0.0021 | 4 |
### Framework versions
- Transformers 4.31.0
- TensorFlow 2.13.0
- Tokenizers 0.13.3