End of training
Browse files- README.md +79 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
base_model: facebook/mms-1b-all
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: wav2vec2-large-mms-1b-kazakh-speech2ner-ksc_t-16b-4ep
|
| 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 |
+
# wav2vec2-large-mms-1b-kazakh-speech2ner-ksc_t-16b-4ep
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.2397
|
| 21 |
+
- Wer: 0.3099
|
| 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: 1e-05
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 1000
|
| 48 |
+
- num_epochs: 4
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 54 |
+
| 0.3934 | 0.22 | 2000 | 0.3610 | 0.3687 |
|
| 55 |
+
| 0.3361 | 0.43 | 4000 | 0.2983 | 0.3412 |
|
| 56 |
+
| 0.3211 | 0.65 | 6000 | 0.2779 | 0.3300 |
|
| 57 |
+
| 0.3146 | 0.87 | 8000 | 0.2685 | 0.3238 |
|
| 58 |
+
| 0.3104 | 1.09 | 10000 | 0.2613 | 0.3210 |
|
| 59 |
+
| 0.2965 | 1.3 | 12000 | 0.2571 | 0.3188 |
|
| 60 |
+
| 0.3004 | 1.52 | 14000 | 0.2531 | 0.3166 |
|
| 61 |
+
| 0.2889 | 1.74 | 16000 | 0.2504 | 0.3153 |
|
| 62 |
+
| 0.2955 | 1.96 | 18000 | 0.2476 | 0.3138 |
|
| 63 |
+
| 0.2869 | 2.17 | 20000 | 0.2465 | 0.3126 |
|
| 64 |
+
| 0.2855 | 2.39 | 22000 | 0.2443 | 0.3117 |
|
| 65 |
+
| 0.2927 | 2.61 | 24000 | 0.2431 | 0.3111 |
|
| 66 |
+
| 0.2789 | 2.83 | 26000 | 0.2421 | 0.3107 |
|
| 67 |
+
| 0.2854 | 3.04 | 28000 | 0.2412 | 0.3105 |
|
| 68 |
+
| 0.2918 | 3.26 | 30000 | 0.2404 | 0.3099 |
|
| 69 |
+
| 0.2768 | 3.48 | 32000 | 0.2401 | 0.3096 |
|
| 70 |
+
| 0.2771 | 3.69 | 34000 | 0.2398 | 0.3099 |
|
| 71 |
+
| 0.2733 | 3.91 | 36000 | 0.2397 | 0.3099 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.33.0.dev0
|
| 77 |
+
- Pytorch 2.0.1+cu117
|
| 78 |
+
- Datasets 2.13.1
|
| 79 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3859370253
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa438491aec161c9fac3a4162c4a8aeb56296a3804ce3587131ac866c89b344b
|
| 3 |
size 3859370253
|