Update stats.md
Browse files
stats.md
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- 'no'
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
base_model: NbAiLab/nb-whisper-medium-RC1
|
| 6 |
+
tags:
|
| 7 |
+
- audio
|
| 8 |
+
- asr
|
| 9 |
+
- automatic-speech-recognition
|
| 10 |
+
- hf-asr-leaderboard
|
| 11 |
+
model-index:
|
| 12 |
+
- name: nb-whisper-medium-v0.8-vad3
|
| 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-medium-v0.8-vad3
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [NbAiLab/nb-whisper-medium-RC1](https://huggingface.co/NbAiLab/nb-whisper-medium-RC1) on the NbAiLab/ncc_speech_styling_v2_vad3 dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- step: 49999
|
| 24 |
+
- validation_nst_loss: 0.4365
|
| 25 |
+
- train_loss: 0.4233
|
| 26 |
+
- validation_nst_wer: 2.4062
|
| 27 |
+
- validation_nst_cer: 0.7262
|
| 28 |
+
- validation_nst_exact_wer: 3.0867
|
| 29 |
+
- validation_nst_exact_cer: 0.8297
|
| 30 |
+
- validation_clean_stortinget_no_loss: 0.7815
|
| 31 |
+
- validation_clean_stortinget_no_wer: 9.0005
|
| 32 |
+
- validation_clean_stortinget_no_cer: 5.7907
|
| 33 |
+
- validation_clean_stortinget_no_exact_wer: 12.1101
|
| 34 |
+
- validation_clean_stortinget_no_exact_cer: 6.2732
|
| 35 |
+
|
| 36 |
+
## Model description
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Intended uses & limitations
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training and evaluation data
|
| 45 |
+
|
| 46 |
+
More information needed
|
| 47 |
+
|
| 48 |
+
## Training procedure
|
| 49 |
+
|
| 50 |
+
### Training hyperparameters
|
| 51 |
+
|
| 52 |
+
The following hyperparameters were used during training:
|
| 53 |
+
- learning_rate: 2.5e-05
|
| 54 |
+
- lr_scheduler_type: linear
|
| 55 |
+
- per_device_train_batch_size: 32
|
| 56 |
+
- total_train_batch_size_per_node: 128
|
| 57 |
+
- total_train_batch_size: 1024
|
| 58 |
+
- total_optimization_steps: 50,000
|
| 59 |
+
- starting_optimization_step: None
|
| 60 |
+
- finishing_optimization_step: 50,000
|
| 61 |
+
- num_train_dataset_workers: 32
|
| 62 |
+
- num_hosts: 8
|
| 63 |
+
- total_num_training_examples: 51,200,000
|
| 64 |
+
- steps_per_epoch: 7455
|
| 65 |
+
- num_beams: None
|
| 66 |
+
- weight_decay: 0.01
|
| 67 |
+
- adam_beta1: 0.9
|
| 68 |
+
- adam_beta2: 0.98
|
| 69 |
+
- adam_epsilon: 1e-06
|
| 70 |
+
- dropout: True
|
| 71 |
+
- bpe_dropout_probability: 0.2
|
| 72 |
+
- activation_dropout_probability: 0.1
|
| 73 |
+
|
| 74 |
+
### Training results
|
| 75 |
+
|
| 76 |
+
| step | validation_nst_loss | train_loss | validation_nst_wer | validation_nst_cer | validation_nst_exact_wer | validation_nst_exact_cer | validation_clean_stortinget_no_loss | validation_clean_stortinget_no_wer | validation_clean_stortinget_no_cer | validation_clean_stortinget_no_exact_wer | validation_clean_stortinget_no_exact_cer |
|
| 77 |
+
|:-----:|:-------------------:|:----------:|:------------------:|:------------------:|:------------------------:|:------------------------:|:-----------------------------------:|:----------------------------------:|:----------------------------------:|:----------------------------------------:|:----------------------------------------:|
|
| 78 |
+
| 0 | 0.4223 | 0.8343 | 2.3463 | 0.7206 | 2.9397 | 0.8105 | 0.6313 | 8.8868 | 5.7697 | 11.8752 | 6.2280 |
|
| 79 |
+
| 5000 | 0.4364 | 0.5289 | 2.6077 | 0.8063 | 3.2555 | 0.9057 | 0.6300 | 9.1071 | 5.8300 | 12.0840 | 6.3028 |
|
| 80 |
+
| 10000 | 0.4353 | 0.4901 | 2.4824 | 0.7765 | 3.0867 | 0.8709 | 0.6463 | 9.2563 | 5.9382 | 12.2144 | 6.4042 |
|
| 81 |
+
| 15000 | 0.4338 | 0.4760 | 2.4062 | 0.7290 | 3.0541 | 0.8324 | 0.6788 | 9.0052 | 5.7931 | 12.0816 | 6.2720 |
|
| 82 |
+
| 20000 | 0.4343 | 0.4553 | 2.5695 | 0.7868 | 3.1956 | 0.8819 | 0.7058 | 9.1710 | 5.9434 | 12.2168 | 6.4280 |
|
| 83 |
+
| 25000 | 0.4399 | 0.4476 | 2.4171 | 0.7439 | 3.0486 | 0.8398 | 0.7342 | 9.2800 | 5.9227 | 12.3947 | 6.4081 |
|
| 84 |
+
| 30000 | 0.4356 | 0.4395 | 2.4008 | 0.7327 | 3.0377 | 0.8288 | 0.7352 | 9.2279 | 5.9985 | 12.2975 | 6.4826 |
|
| 85 |
+
| 35000 | 0.4365 | 0.4371 | 2.5587 | 0.7756 | 3.2174 | 0.8764 | 0.7505 | 9.1852 | 5.8557 | 12.2714 | 6.3383 |
|
| 86 |
+
| 40000 | 0.4358 | 0.4271 | 2.4607 | 0.7374 | 3.1248 | 0.8389 | 0.7643 | 9.1118 | 5.8569 | 12.2334 | 6.3449 |
|
| 87 |
+
| 45000 | 0.4360 | 0.4211 | 2.5042 | 0.7458 | 3.0867 | 0.8334 | 0.7833 | 9.1094 | 5.8625 | 12.1646 | 6.3383 |
|
| 88 |
+
| 49999 | 0.4365 | 0.4233 | 2.4062 | 0.7262 | 3.0867 | 0.8297 |
|
| 89 |
+
| 49999 | 0.7815 | 0.4233 | 9.0005 | 5.7907 | 12.1101 | 6.2732 |
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
### Framework versions
|
| 93 |
+
|
| 94 |
+
- Transformers 4.34.1
|
| 95 |
+
- Datasets 2.16.1
|
| 96 |
+
- Tokenizers 0.14.1
|