Commit
•
3223873
1
Parent(s):
a871a21
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- audiofolder
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: whisper-medium-Bambara-field
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Automatic Speech Recognition
|
| 14 |
+
type: automatic-speech-recognition
|
| 15 |
+
dataset:
|
| 16 |
+
name: audiofolder
|
| 17 |
+
type: audiofolder
|
| 18 |
+
config: default
|
| 19 |
+
split: train
|
| 20 |
+
args: default
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Wer
|
| 23 |
+
type: wer
|
| 24 |
+
value: 159.03091832025842
|
| 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-medium-Bambara-field
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the audiofolder dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 5.3800
|
| 35 |
+
- Wer: 159.0309
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 1e-05
|
| 55 |
+
- train_batch_size: 16
|
| 56 |
+
- eval_batch_size: 2
|
| 57 |
+
- seed: 42
|
| 58 |
+
- distributed_type: multi-GPU
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- lr_scheduler_warmup_steps: 500
|
| 62 |
+
- training_steps: 13532
|
| 63 |
+
- mixed_precision_training: Native AMP
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 68 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 69 |
+
| 0.6342 | 1.03 | 1000 | 2.5810 | 159.5293 |
|
| 70 |
+
| 0.2873 | 3.03 | 2000 | 2.9513 | 159.1140 |
|
| 71 |
+
| 0.1461 | 5.02 | 3000 | 3.6833 | 158.3941 |
|
| 72 |
+
| 0.049 | 7.02 | 4000 | 4.0725 | 157.6004 |
|
| 73 |
+
| 0.0218 | 9.01 | 5000 | 4.2531 | 158.3664 |
|
| 74 |
+
| 0.0071 | 11.0 | 6000 | 4.5944 | 157.9972 |
|
| 75 |
+
| 0.0057 | 12.04 | 7000 | 4.6659 | 161.4952 |
|
| 76 |
+
| 0.0061 | 14.03 | 8000 | 4.9162 | 161.0614 |
|
| 77 |
+
| 0.0042 | 16.03 | 9000 | 5.0205 | 158.9848 |
|
| 78 |
+
| 0.0007 | 18.02 | 10000 | 5.1463 | 159.1970 |
|
| 79 |
+
| 0.0015 | 20.01 | 11000 | 5.2150 | 159.0401 |
|
| 80 |
+
| 0.0001 | 22.01 | 12000 | 5.3008 | 159.5478 |
|
| 81 |
+
| 0.0001 | 24.0 | 13000 | 5.3800 | 159.0309 |
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
### Framework versions
|
| 85 |
+
|
| 86 |
+
- Transformers 4.25.1
|
| 87 |
+
- Pytorch 1.13.1+cu117
|
| 88 |
+
- Datasets 2.8.0
|
| 89 |
+
- Tokenizers 0.13.2
|