Commit
•
0626af3
1
Parent(s):
4beca20
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- librispeech_asr
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-large-xls-r-300m-en-libri-more-steps
|
| 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-large-xls-r-300m-en-libri-more-steps
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the librispeech_asr dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.7624
|
| 20 |
+
- Wer: 0.8772
|
| 21 |
+
- Cer: 0.3762
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.001
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 100
|
| 49 |
+
- num_epochs: 20
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
| 55 |
+
| No log | 1.94 | 33 | 2.9987 | 1.0 | 1.0 |
|
| 56 |
+
| No log | 3.88 | 66 | 2.8951 | 1.0 | 1.0 |
|
| 57 |
+
| No log | 5.82 | 99 | 2.8732 | 1.0 | 1.0 |
|
| 58 |
+
| 3.781 | 7.76 | 132 | 2.6057 | 1.0 | 1.0 |
|
| 59 |
+
| 3.781 | 9.71 | 165 | 1.9015 | 1.0154 | 0.5616 |
|
| 60 |
+
| 3.781 | 11.65 | 198 | 1.5226 | 0.9263 | 0.4462 |
|
| 61 |
+
| 2.2258 | 13.59 | 231 | 1.5116 | 0.8913 | 0.3967 |
|
| 62 |
+
| 2.2258 | 15.53 | 264 | 1.5634 | 0.8922 | 0.3842 |
|
| 63 |
+
| 2.2258 | 17.47 | 297 | 1.7016 | 0.8876 | 0.3796 |
|
| 64 |
+
| 0.7946 | 19.41 | 330 | 1.7624 | 0.8772 | 0.3762 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.20.1
|
| 70 |
+
- Pytorch 1.11.0+cpu
|
| 71 |
+
- Datasets 1.18.3
|
| 72 |
+
- Tokenizers 0.12.1
|