End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_longertrain
|
| 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_longertrain
|
| 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: 1.1396
|
| 21 |
+
- Wer: 0.2973
|
| 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: 15
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 1.4721 | 0.43 | 100 | 1.0565 | 0.4014 |
|
| 54 |
+
| 1.2574 | 0.85 | 200 | 0.9707 | 0.3704 |
|
| 55 |
+
| 1.1397 | 1.28 | 300 | 0.9644 | 0.3609 |
|
| 56 |
+
| 1.0939 | 1.71 | 400 | 0.9610 | 0.3637 |
|
| 57 |
+
| 1.0874 | 2.14 | 500 | 0.9508 | 0.3581 |
|
| 58 |
+
| 1.0573 | 2.56 | 600 | 0.8865 | 0.3518 |
|
| 59 |
+
| 1.0386 | 2.99 | 700 | 1.0304 | 0.3493 |
|
| 60 |
+
| 0.9792 | 3.42 | 800 | 0.8235 | 0.3523 |
|
| 61 |
+
| 0.9789 | 3.85 | 900 | 0.8404 | 0.3388 |
|
| 62 |
+
| 0.9095 | 4.27 | 1000 | 1.0925 | 0.3588 |
|
| 63 |
+
| 0.8947 | 4.7 | 1100 | 1.0126 | 0.3357 |
|
| 64 |
+
| 0.8571 | 5.13 | 1200 | 1.1404 | 0.3550 |
|
| 65 |
+
| 0.8276 | 5.56 | 1300 | 0.8135 | 0.3294 |
|
| 66 |
+
| 0.8631 | 5.98 | 1400 | 0.8342 | 0.3279 |
|
| 67 |
+
| 0.8134 | 6.41 | 1500 | 0.8524 | 0.3177 |
|
| 68 |
+
| 0.8027 | 6.84 | 1600 | 0.8182 | 0.3207 |
|
| 69 |
+
| 0.7556 | 7.26 | 1700 | 0.8445 | 0.3185 |
|
| 70 |
+
| 0.737 | 7.69 | 1800 | 0.8919 | 0.3197 |
|
| 71 |
+
| 0.7398 | 8.12 | 1900 | 0.8115 | 0.3167 |
|
| 72 |
+
| 0.7069 | 8.55 | 2000 | 0.8346 | 0.3174 |
|
| 73 |
+
| 0.7206 | 8.97 | 2100 | 0.9714 | 0.3147 |
|
| 74 |
+
| 0.6946 | 9.4 | 2200 | 0.8138 | 0.3124 |
|
| 75 |
+
| 0.6752 | 9.83 | 2300 | 0.8366 | 0.3086 |
|
| 76 |
+
| 0.7256 | 10.26 | 2400 | 0.8482 | 0.3044 |
|
| 77 |
+
| 0.7063 | 10.68 | 2500 | 0.8997 | 0.3041 |
|
| 78 |
+
| 0.6399 | 11.11 | 2600 | 0.8614 | 0.3045 |
|
| 79 |
+
| 0.6268 | 11.54 | 2700 | 0.8564 | 0.3018 |
|
| 80 |
+
| 0.6665 | 11.97 | 2800 | 0.8531 | 0.3006 |
|
| 81 |
+
| 0.622 | 12.39 | 2900 | 0.8759 | 0.3007 |
|
| 82 |
+
| 0.6568 | 12.82 | 3000 | 1.3093 | 0.3023 |
|
| 83 |
+
| 0.6296 | 13.25 | 3100 | 1.1312 | 0.3002 |
|
| 84 |
+
| 0.6448 | 13.68 | 3200 | 1.1779 | 0.2994 |
|
| 85 |
+
| 0.6188 | 14.1 | 3300 | 1.1203 | 0.2989 |
|
| 86 |
+
| 0.6216 | 14.53 | 3400 | 1.1421 | 0.2978 |
|
| 87 |
+
| 0.6238 | 14.96 | 3500 | 1.1396 | 0.2973 |
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
### Framework versions
|
| 91 |
+
|
| 92 |
+
- Transformers 4.38.2
|
| 93 |
+
- Pytorch 2.2.1+cu121
|
| 94 |
+
- Datasets 2.18.0
|
| 95 |
+
- 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 sha256:533633436c982e4956bf0e9b86e1088aec028cadfb0e6feaed9ddec4f1e062ac
|
| 3 |
size 377611120
|
runs/Apr13_02-47-21_0a3cd2114bd2/events.out.tfevents.1712976617.0a3cd2114bd2.1264.3
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 sha256:3bdeb62b6d070d759da569d4a9e6aad00ffa023de9772733a8225d6462d0c3f2
|
| 3 |
+
size 24948
|