End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/wav2vec2-base-960h
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: wav2vecvanilla_ctc_zero_infinity
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# wav2vecvanilla_ctc_zero_infinity
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.8214
|
| 21 |
+
- Wer: 0.3168
|
| 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: 0.0001
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 500
|
| 47 |
+
- num_epochs: 7
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 1.4684 | 0.43 | 100 | 1.0567 | 0.4018 |
|
| 54 |
+
| 1.2572 | 0.85 | 200 | 0.9726 | 0.3706 |
|
| 55 |
+
| 1.139 | 1.28 | 300 | 0.9748 | 0.3602 |
|
| 56 |
+
| 1.0956 | 1.71 | 400 | 0.9989 | 0.3619 |
|
| 57 |
+
| 1.0891 | 2.14 | 500 | 0.9133 | 0.3606 |
|
| 58 |
+
| 1.063 | 2.56 | 600 | 0.9272 | 0.3548 |
|
| 59 |
+
| 1.0339 | 2.99 | 700 | 1.0183 | 0.3444 |
|
| 60 |
+
| 0.9709 | 3.42 | 800 | 0.8244 | 0.3488 |
|
| 61 |
+
| 0.958 | 3.85 | 900 | 0.8335 | 0.3410 |
|
| 62 |
+
| 0.8954 | 4.27 | 1000 | 0.8641 | 0.3336 |
|
| 63 |
+
| 0.8735 | 4.7 | 1100 | 0.8671 | 0.3306 |
|
| 64 |
+
| 0.8411 | 5.13 | 1200 | 0.8373 | 0.3281 |
|
| 65 |
+
| 0.805 | 5.56 | 1300 | 0.8197 | 0.3198 |
|
| 66 |
+
| 0.8452 | 5.98 | 1400 | 0.8343 | 0.3158 |
|
| 67 |
+
| 0.8078 | 6.41 | 1500 | 0.8392 | 0.3165 |
|
| 68 |
+
| 0.7946 | 6.84 | 1600 | 0.8214 | 0.3168 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.38.2
|
| 74 |
+
- Pytorch 2.2.1+cu121
|
| 75 |
+
- Datasets 2.18.0
|
| 76 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377611120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f71109f65a371dedcc1cf151dcadec717dd3009168f7397b6be2fe17e41526d
|
| 3 |
size 377611120
|
runs/Apr13_00-58-42_0a3cd2114bd2/events.out.tfevents.1712970106.0a3cd2114bd2.1264.1
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f99b3ba01b8ebc39500a6f677ea74c2b7db6057f1fd15b941a0aec73b2ed23c9
|
| 3 |
+
size 14860
|