Commit
•
3710a40
1
Parent(s):
be12c1e
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- speech-recognition
|
| 5 |
+
- librispeech_asr
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-librispeech-clean-100h-demo-dist
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# wav2vec2-librispeech-clean-100h-demo-dist
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-lv60](https://huggingface.co/facebook/wav2vec2-large-lv60) on the LIBRISPEECH_ASR - CLEAN dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0572
|
| 20 |
+
- Wer: 0.0417
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0003
|
| 40 |
+
- train_batch_size: 4
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 8
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- total_eval_batch_size: 64
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 500
|
| 50 |
+
- num_epochs: 3.0
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 57 |
+
| 3.399 | 0.11 | 100 | 3.6153 | 1.0 |
|
| 58 |
+
| 2.8892 | 0.22 | 200 | 2.8963 | 1.0 |
|
| 59 |
+
| 2.8284 | 0.34 | 300 | 2.8574 | 1.0 |
|
| 60 |
+
| 0.7347 | 0.45 | 400 | 0.6158 | 0.4850 |
|
| 61 |
+
| 0.1138 | 0.56 | 500 | 0.2038 | 0.1560 |
|
| 62 |
+
| 0.248 | 0.67 | 600 | 0.1274 | 0.1024 |
|
| 63 |
+
| 0.2586 | 0.78 | 700 | 0.1108 | 0.0876 |
|
| 64 |
+
| 0.0733 | 0.9 | 800 | 0.0936 | 0.0762 |
|
| 65 |
+
| 0.044 | 1.01 | 900 | 0.0834 | 0.0662 |
|
| 66 |
+
| 0.0393 | 1.12 | 1000 | 0.0792 | 0.0622 |
|
| 67 |
+
| 0.0941 | 1.23 | 1100 | 0.0769 | 0.0627 |
|
| 68 |
+
| 0.036 | 1.35 | 1200 | 0.0731 | 0.0603 |
|
| 69 |
+
| 0.0768 | 1.46 | 1300 | 0.0713 | 0.0559 |
|
| 70 |
+
| 0.0518 | 1.57 | 1400 | 0.0686 | 0.0537 |
|
| 71 |
+
| 0.0815 | 1.68 | 1500 | 0.0639 | 0.0515 |
|
| 72 |
+
| 0.0603 | 1.79 | 1600 | 0.0636 | 0.0500 |
|
| 73 |
+
| 0.056 | 1.91 | 1700 | 0.0609 | 0.0480 |
|
| 74 |
+
| 0.0265 | 2.02 | 1800 | 0.0621 | 0.0465 |
|
| 75 |
+
| 0.0496 | 2.13 | 1900 | 0.0607 | 0.0449 |
|
| 76 |
+
| 0.0436 | 2.24 | 2000 | 0.0591 | 0.0446 |
|
| 77 |
+
| 0.0421 | 2.35 | 2100 | 0.0590 | 0.0428 |
|
| 78 |
+
| 0.0641 | 2.47 | 2200 | 0.0603 | 0.0443 |
|
| 79 |
+
| 0.0466 | 2.58 | 2300 | 0.0580 | 0.0429 |
|
| 80 |
+
| 0.0132 | 2.69 | 2400 | 0.0574 | 0.0423 |
|
| 81 |
+
| 0.0073 | 2.8 | 2500 | 0.0586 | 0.0417 |
|
| 82 |
+
| 0.0021 | 2.91 | 2600 | 0.0574 | 0.0412 |
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
### Framework versions
|
| 86 |
+
|
| 87 |
+
- Transformers 4.11.0.dev0
|
| 88 |
+
- Pytorch 1.9.0+cu111
|
| 89 |
+
- Datasets 1.12.1
|
| 90 |
+
- Tokenizers 0.10.3
|