Julien Simon
commited on
Commit
•
7bb6f38
1
Parent(s):
866cede
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- speech_commands
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: wav2vec2-conformer-rel-pos-large-finetuned-speech-commands
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# wav2vec2-conformer-rel-pos-large-finetuned-speech-commands
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-conformer-rel-pos-large](https://huggingface.co/facebook/wav2vec2-conformer-rel-pos-large) on the speech_commands dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.5245
|
| 22 |
+
- Accuracy: 0.9724
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 3e-05
|
| 42 |
+
- train_batch_size: 256
|
| 43 |
+
- eval_batch_size: 256
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 4
|
| 46 |
+
- total_train_batch_size: 1024
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 10
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 56 |
+
| 2.2901 | 1.0 | 83 | 2.0542 | 0.8875 |
|
| 57 |
+
| 1.8375 | 2.0 | 166 | 1.5610 | 0.9316 |
|
| 58 |
+
| 1.4957 | 3.0 | 249 | 1.1850 | 0.9558 |
|
| 59 |
+
| 1.1917 | 4.0 | 332 | 0.9159 | 0.9695 |
|
| 60 |
+
| 1.0449 | 5.0 | 415 | 0.7624 | 0.9687 |
|
| 61 |
+
| 0.9319 | 6.0 | 498 | 0.6444 | 0.9715 |
|
| 62 |
+
| 0.8559 | 7.0 | 581 | 0.5806 | 0.9711 |
|
| 63 |
+
| 0.8199 | 8.0 | 664 | 0.5394 | 0.9721 |
|
| 64 |
+
| 0.7949 | 9.0 | 747 | 0.5245 | 0.9724 |
|
| 65 |
+
| 0.7975 | 10.0 | 830 | 0.5256 | 0.9721 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.20.1
|
| 71 |
+
- Pytorch 1.11.0+cu102
|
| 72 |
+
- Datasets 2.3.2
|
| 73 |
+
- Tokenizers 0.12.1
|