Commit
·
be8595f
1
Parent(s):
216e883
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice_11_0
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: whisper-small-pt-cv11-v4_2
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Automatic Speech Recognition
|
| 14 |
+
type: automatic-speech-recognition
|
| 15 |
+
dataset:
|
| 16 |
+
name: common_voice_11_0
|
| 17 |
+
type: common_voice_11_0
|
| 18 |
+
config: pt
|
| 19 |
+
split: test
|
| 20 |
+
args: pt
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Wer
|
| 23 |
+
type: wer
|
| 24 |
+
value: 14.28351309707242
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# whisper-small-pt-cv11-v4_2
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_11_0 dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.2995
|
| 35 |
+
- Wer: 14.2835
|
| 36 |
+
- Cer: 5.5623
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 5e-06
|
| 56 |
+
- train_batch_size: 32
|
| 57 |
+
- eval_batch_size: 16
|
| 58 |
+
- seed: 42
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- lr_scheduler_warmup_steps: 1000
|
| 62 |
+
- training_steps: 10000
|
| 63 |
+
- mixed_precision_training: Native AMP
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
|
| 69 |
+
| 1.1113 | 0.92 | 500 | 0.3897 | 16.8721 | 6.7919 |
|
| 70 |
+
| 0.9009 | 1.84 | 1000 | 0.3318 | 15.9322 | 6.2310 |
|
| 71 |
+
| 0.7631 | 2.76 | 1500 | 0.3177 | 15.4854 | 5.8939 |
|
| 72 |
+
| 0.7163 | 3.68 | 2000 | 0.3130 | 14.8998 | 5.7972 |
|
| 73 |
+
| 0.6334 | 4.6 | 2500 | 0.3034 | 14.7920 | 5.6867 |
|
| 74 |
+
| 0.5746 | 5.52 | 3000 | 0.3029 | 14.6225 | 5.6397 |
|
| 75 |
+
| 0.5359 | 6.45 | 3500 | 0.3018 | 14.4838 | 5.5789 |
|
| 76 |
+
| 0.5058 | 7.37 | 4000 | 0.3010 | 14.5917 | 5.6839 |
|
| 77 |
+
| 0.4833 | 8.29 | 4500 | 0.3023 | 14.2373 | 5.5236 |
|
| 78 |
+
| 0.4398 | 9.21 | 5000 | 0.3005 | 14.4222 | 5.5844 |
|
| 79 |
+
| 0.4359 | 10.13 | 5500 | 0.2999 | 14.4838 | 5.6259 |
|
| 80 |
+
| 0.4036 | 11.05 | 6000 | 0.2995 | 14.2835 | 5.5623 |
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Framework versions
|
| 84 |
+
|
| 85 |
+
- Transformers 4.26.0.dev0
|
| 86 |
+
- Pytorch 1.12.1+cu116
|
| 87 |
+
- Datasets 2.7.1.dev0
|
| 88 |
+
- Tokenizers 0.13.2
|