Commit
•
b87ec76
1
Parent(s):
20aea44
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: whisper-large-et-clinic
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# whisper-large-et-clinic
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [agnesluhtaru/whisper-large-et-ERR2020-v2](https://huggingface.co/agnesluhtaru/whisper-large-et-ERR2020-v2) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4132
|
| 20 |
+
- Wer: 15.7347
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 1e-05
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 16
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 200
|
| 48 |
+
- training_steps: 4000
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 55 |
+
| 0.0297 | 4.03 | 500 | 0.3037 | 16.7147 |
|
| 56 |
+
| 0.0057 | 8.06 | 1000 | 0.3435 | 15.9496 |
|
| 57 |
+
| 0.0049 | 12.1 | 1500 | 0.3610 | 16.8737 |
|
| 58 |
+
| 0.0015 | 16.13 | 2000 | 0.3610 | 16.1258 |
|
| 59 |
+
| 0.001 | 20.16 | 2500 | 0.3868 | 16.0356 |
|
| 60 |
+
| 0.0011 | 24.19 | 3000 | 0.3949 | 15.8293 |
|
| 61 |
+
| 0.0006 | 28.22 | 3500 | 0.4028 | 15.7476 |
|
| 62 |
+
| 0.0008 | 32.26 | 4000 | 0.4132 | 15.7347 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.26.0.dev0
|
| 68 |
+
- Pytorch 1.12.1+rocm5.1.1
|
| 69 |
+
- Datasets 2.7.1.dev0
|
| 70 |
+
- Tokenizers 0.13.2
|