End of training
Browse files
README.md
CHANGED
|
@@ -8,9 +8,24 @@ tags:
|
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- mozilla-foundation/common_voice_11_0
|
|
|
|
|
|
|
| 11 |
model-index:
|
| 12 |
- name: Whisper Small bn - Group 4
|
| 13 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -19,6 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
# Whisper Small bn - Group 4
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -43,10 +61,23 @@ The following hyperparameters were used during training:
|
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
-
-
|
| 47 |
-
- training_steps: 5000
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
### Framework versions
|
| 51 |
|
| 52 |
- Transformers 4.36.0.dev0
|
|
|
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- mozilla-foundation/common_voice_11_0
|
| 11 |
+
metrics:
|
| 12 |
+
- wer
|
| 13 |
model-index:
|
| 14 |
- name: Whisper Small bn - Group 4
|
| 15 |
+
results:
|
| 16 |
+
- task:
|
| 17 |
+
name: Automatic Speech Recognition
|
| 18 |
+
type: automatic-speech-recognition
|
| 19 |
+
dataset:
|
| 20 |
+
name: Common Voice 11.0
|
| 21 |
+
type: mozilla-foundation/common_voice_11_0
|
| 22 |
+
config: default
|
| 23 |
+
split: test
|
| 24 |
+
args: 'config: bn, split: test'
|
| 25 |
+
metrics:
|
| 26 |
+
- name: Wer
|
| 27 |
+
type: wer
|
| 28 |
+
value: 43.03652465083491
|
| 29 |
---
|
| 30 |
|
| 31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 34 |
# Whisper Small bn - Group 4
|
| 35 |
|
| 36 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
| 37 |
+
It achieves the following results on the evaluation set:
|
| 38 |
+
- Loss: 0.2531
|
| 39 |
+
- Wer: 43.0365
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
|
|
|
| 61 |
- seed: 42
|
| 62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 63 |
- lr_scheduler_type: linear
|
| 64 |
+
- training_steps: 4000
|
|
|
|
| 65 |
- mixed_precision_training: Native AMP
|
| 66 |
|
| 67 |
+
### Training results
|
| 68 |
+
|
| 69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 70 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 71 |
+
| 0.1467 | 1.06 | 500 | 0.1944 | 52.8704 |
|
| 72 |
+
| 0.0769 | 2.12 | 1000 | 0.1651 | 47.0106 |
|
| 73 |
+
| 0.044 | 3.18 | 1500 | 0.1693 | 45.1381 |
|
| 74 |
+
| 0.0203 | 4.24 | 2000 | 0.1860 | 43.4903 |
|
| 75 |
+
| 0.0097 | 5.3 | 2500 | 0.2096 | 43.9618 |
|
| 76 |
+
| 0.0039 | 6.36 | 3000 | 0.2311 | 43.2877 |
|
| 77 |
+
| 0.0019 | 7.42 | 3500 | 0.2454 | 43.2612 |
|
| 78 |
+
| 0.0009 | 8.47 | 4000 | 0.2531 | 43.0365 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
### Framework versions
|
| 82 |
|
| 83 |
- Transformers 4.36.0.dev0
|