Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: openai/whisper-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: whisper-base-cdsd1h-lora
|
| 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-base-cdsd1h-lora
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.1538
|
| 22 |
+
- Wer: 80.9311
|
| 23 |
+
- Cer: 54.8108
|
| 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: 0.001
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 100
|
| 49 |
+
- num_epochs: 10
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
| 56 |
+
| 1.26 | 1.0 | 559 | 1.2699 | 88.5407 | 75.2064 |
|
| 57 |
+
| 0.9831 | 2.0 | 1118 | 1.1855 | 86.8845 | 68.5931 |
|
| 58 |
+
| 0.8122 | 3.0 | 1677 | 1.1086 | 82.5873 | 66.3942 |
|
| 59 |
+
| 0.6565 | 4.0 | 2236 | 1.0974 | 83.6616 | 71.2172 |
|
| 60 |
+
| 0.5474 | 5.0 | 2795 | 1.0791 | 82.5425 | 57.2223 |
|
| 61 |
+
| 0.4118 | 6.0 | 3354 | 1.0899 | 81.1996 | 57.5084 |
|
| 62 |
+
| 0.2976 | 7.0 | 3913 | 1.1049 | 81.1996 | 55.4729 |
|
| 63 |
+
| 0.1923 | 8.0 | 4472 | 1.1130 | 80.8863 | 57.0343 |
|
| 64 |
+
| 0.1222 | 9.0 | 5031 | 1.1395 | 80.7968 | 55.4974 |
|
| 65 |
+
| 0.073 | 10.0 | 5590 | 1.1538 | 80.9311 | 54.8108 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- PEFT 0.13.2
|
| 71 |
+
- Transformers 4.44.2
|
| 72 |
+
- Pytorch 2.0.0+cu118
|
| 73 |
+
- Datasets 2.19.1
|
| 74 |
+
- Tokenizers 0.19.1
|
runs/Nov24_01-03-38_WIN-CEJF2NB9KFH/events.out.tfevents.1732381420.WIN-CEJF2NB9KFH.4396.0
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 sha256:195873c3f57ce30127f2f57263f22add81903a13d3aa699efa1dc5b3e7fc7557
|
| 3 |
+
size 56897
|