End of training
Browse files- README.md +77 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: openai/whisper-large-v3
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: whisper-large-v3-chichewa-variant-b-normalized-transcript
|
| 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 |
+
# whisper-large-v3-chichewa-variant-b-normalized-transcript
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.3983
|
| 22 |
+
- Wer: 59.3004
|
| 23 |
+
- Cer: 28.1383
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 7.5e-06
|
| 43 |
+
- train_batch_size: 8
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 4
|
| 47 |
+
- total_train_batch_size: 32
|
| 48 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_steps: 0.05
|
| 51 |
+
- training_steps: 3000
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 56 |
+
|:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:|
|
| 57 |
+
| 6.1874 | 0.9259 | 100 | 1.4766 | 82.4754 | 37.1937 |
|
| 58 |
+
| 4.3049 | 1.8519 | 200 | 1.1418 | 74.2396 | 35.4061 |
|
| 59 |
+
| 3.2137 | 2.7778 | 300 | 1.0356 | 62.0496 | 28.7776 |
|
| 60 |
+
| 2.3819 | 3.7037 | 400 | 1.0180 | 61.5466 | 27.8582 |
|
| 61 |
+
| 1.7253 | 4.6296 | 500 | 1.0404 | 61.4998 | 29.3362 |
|
| 62 |
+
| 1.2334 | 5.5556 | 600 | 1.1001 | 57.9902 | 27.0954 |
|
| 63 |
+
| 0.7779 | 6.4815 | 700 | 1.1463 | 59.2302 | 28.1762 |
|
| 64 |
+
| 0.5770 | 7.4074 | 800 | 1.2063 | 57.3701 | 26.3506 |
|
| 65 |
+
| 0.3544 | 8.3333 | 900 | 1.2435 | 61.1254 | 28.6804 |
|
| 66 |
+
| 0.2340 | 9.2593 | 1000 | 1.3227 | 59.6280 | 28.2108 |
|
| 67 |
+
| 0.1444 | 10.1852 | 1100 | 1.3311 | 57.8147 | 26.0277 |
|
| 68 |
+
| 0.1176 | 11.1111 | 1200 | 1.3743 | 57.6626 | 26.5121 |
|
| 69 |
+
| 0.1288 | 12.0370 | 1300 | 1.3983 | 59.3004 | 28.1383 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 5.8.1
|
| 75 |
+
- Pytorch 2.6.0+cu124
|
| 76 |
+
- Datasets 3.6.0
|
| 77 |
+
- Tokenizers 0.22.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6174112552
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24e320f93cb15f71a4280e54d92e1974d7a5784768e6d5f19e86429cb656643e
|
| 3 |
size 6174112552
|