End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: openai/whisper-base
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:openai/whisper-base
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
metrics:
|
| 10 |
+
- wer
|
| 11 |
+
model-index:
|
| 12 |
+
- name: whisper-small-finetuned-multilingual-on-kaggle
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# whisper-small-finetuned-multilingual-on-kaggle
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.6732
|
| 24 |
+
- Wer: 191.2033
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 1e-05
|
| 44 |
+
- train_batch_size: 32
|
| 45 |
+
- eval_batch_size: 64
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 500
|
| 50 |
+
- training_steps: 5000
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 56 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
| 57 |
+
| No log | 0 | 0 | 2.0460 | 162.1874 |
|
| 58 |
+
| 0.3398 | 2.2523 | 1000 | 1.8079 | 181.3942 |
|
| 59 |
+
| 0.3015 | 4.5045 | 2000 | 1.7287 | 176.3787 |
|
| 60 |
+
| 0.2972 | 6.7568 | 3000 | 1.6952 | 184.4728 |
|
| 61 |
+
| 0.2783 | 9.0090 | 4000 | 1.6783 | 183.3356 |
|
| 62 |
+
| 0.2877 | 11.2613 | 5000 | 1.6732 | 191.2033 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- PEFT 0.17.1
|
| 68 |
+
- Transformers 4.56.1
|
| 69 |
+
- Pytorch 2.6.0+cu124
|
| 70 |
+
- Datasets 3.6.0
|
| 71 |
+
- Tokenizers 0.22.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1189560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd3a831b6b709ec2fb518474f10cadd319e8c7a858bd6bc589d4c8228db06e2f
|
| 3 |
size 1189560
|
runs/Sep07_10-51-55_c1882a389259/events.out.tfevents.1757242316.c1882a389259.19.0
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:b5a59afffc1425d022924288054539a1270ff5486b4f39f2810ebf48a943d78a
|
| 3 |
+
size 51691
|