Update stats.md
Browse files
stats.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- 'no'
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
base_model: NbAiLab/nb-whisper-base-v0.8-vad3
|
| 6 |
+
tags:
|
| 7 |
+
- audio
|
| 8 |
+
- asr
|
| 9 |
+
- automatic-speech-recognition
|
| 10 |
+
- hf-asr-leaderboard
|
| 11 |
+
model-index:
|
| 12 |
+
- name: nb-whisper-base-v0.8-vad3-verbatim
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 17 |
+
probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# nb-whisper-base-v0.8-vad3-verbatim
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [NbAiLab/nb-whisper-base-v0.8-vad3](https://huggingface.co/NbAiLab/nb-whisper-base-v0.8-vad3) on the NbAiLab/NPSC dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- step: 249
|
| 24 |
+
- validation_loss: 0.5419
|
| 25 |
+
- train_loss: 0.4718
|
| 26 |
+
- validation_wer: 11.3249
|
| 27 |
+
- validation_cer: 3.9000
|
| 28 |
+
- validation_exact_wer: 11.5693
|
| 29 |
+
- validation_exact_cer: 3.9375
|
| 30 |
+
|
| 31 |
+
## Model description
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Intended uses & limitations
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training and evaluation data
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training procedure
|
| 44 |
+
|
| 45 |
+
### Training hyperparameters
|
| 46 |
+
|
| 47 |
+
The following hyperparameters were used during training:
|
| 48 |
+
- learning_rate: 0.0001
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- per_device_train_batch_size: 32
|
| 51 |
+
- total_train_batch_size_per_node: 128
|
| 52 |
+
- total_train_batch_size: 1024
|
| 53 |
+
- total_optimization_steps: 250
|
| 54 |
+
- starting_optimization_step: None
|
| 55 |
+
- finishing_optimization_step: 250
|
| 56 |
+
- num_train_dataset_workers: 32
|
| 57 |
+
- num_hosts: 8
|
| 58 |
+
- total_num_training_examples: 256,000
|
| 59 |
+
- steps_per_epoch: 45
|
| 60 |
+
- num_beams: None
|
| 61 |
+
- weight_decay: 0.01
|
| 62 |
+
- adam_beta1: 0.9
|
| 63 |
+
- adam_beta2: 0.98
|
| 64 |
+
- adam_epsilon: 1e-06
|
| 65 |
+
- dropout: True
|
| 66 |
+
- bpe_dropout_probability: 0.2
|
| 67 |
+
- activation_dropout_probability: 0.1
|
| 68 |
+
|
| 69 |
+
### Training results
|
| 70 |
+
|
| 71 |
+
| step | validation_loss | train_loss | validation_wer | validation_cer | validation_exact_wer | validation_exact_cer |
|
| 72 |
+
|:----:|:---------------:|:----------:|:--------------:|:--------------:|:--------------------:|:--------------------:|
|
| 73 |
+
| 0 | 1.2371 | 1.2082 | 21.0503 | 11.5619 | 35.6160 | 14.7314 |
|
| 74 |
+
| 40 | 0.5799 | 0.5877 | 13.1592 | 4.4751 | 13.4138 | 4.5352 |
|
| 75 |
+
| 80 | 0.5521 | 0.5398 | 11.8506 | 4.0542 | 12.0939 | 4.0935 |
|
| 76 |
+
| 120 | 0.5469 | 0.4995 | 11.6884 | 3.9923 | 11.9641 | 4.0345 |
|
| 77 |
+
| 160 | 0.5441 | 0.4875 | 11.3864 | 3.9305 | 11.6257 | 3.9651 |
|
| 78 |
+
| 200 | 0.5422 | 0.4770 | 11.3808 | 3.9209 | 11.6370 | 3.9631 |
|
| 79 |
+
| 240 | 0.5417 | 0.4789 | 11.2913 | 3.8886 | 11.5241 | 3.9251 |
|
| 80 |
+
| 249 | 0.5419 | 0.4718 | 11.3249 | 3.9000 | 11.5693 | 3.9375 |
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Framework versions
|
| 84 |
+
|
| 85 |
+
- Transformers 4.34.1
|
| 86 |
+
- Datasets 2.16.1
|
| 87 |
+
- Tokenizers 0.14.1
|