Final model with Model Card
Browse files
README.md
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/hubert-large-ls960-ft
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- fleurs
|
| 9 |
+
metrics:
|
| 10 |
+
- wer
|
| 11 |
+
model-index:
|
| 12 |
+
- name: speech-to-text-model2
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Automatic Speech Recognition
|
| 16 |
+
type: automatic-speech-recognition
|
| 17 |
+
dataset:
|
| 18 |
+
name: fleurs
|
| 19 |
+
type: fleurs
|
| 20 |
+
config: en_us
|
| 21 |
+
split: None
|
| 22 |
+
args: en_us
|
| 23 |
+
metrics:
|
| 24 |
+
- name: Wer
|
| 25 |
+
type: wer
|
| 26 |
+
value: 0.12054313689266581
|
| 27 |
+
---
|
| 28 |
+
|
| 29 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 30 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 31 |
+
|
| 32 |
+
# speech-to-text-model2
|
| 33 |
+
|
| 34 |
+
This model is a fine-tuned version of [facebook/hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft) on the fleurs dataset.
|
| 35 |
+
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.1971
|
| 37 |
+
- Wer: 0.1205
|
| 38 |
+
|
| 39 |
+
## Model description
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Intended uses & limitations
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training and evaluation data
|
| 48 |
+
|
| 49 |
+
More information needed
|
| 50 |
+
|
| 51 |
+
## Training procedure
|
| 52 |
+
|
| 53 |
+
### Training hyperparameters
|
| 54 |
+
|
| 55 |
+
The following hyperparameters were used during training:
|
| 56 |
+
- learning_rate: 3e-05
|
| 57 |
+
- train_batch_size: 2
|
| 58 |
+
- eval_batch_size: 2
|
| 59 |
+
- seed: 42
|
| 60 |
+
- gradient_accumulation_steps: 2
|
| 61 |
+
- total_train_batch_size: 4
|
| 62 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 63 |
+
- lr_scheduler_type: linear
|
| 64 |
+
- lr_scheduler_warmup_steps: 500
|
| 65 |
+
- num_epochs: 4
|
| 66 |
+
- mixed_precision_training: Native AMP
|
| 67 |
+
|
| 68 |
+
### Training results
|
| 69 |
+
|
| 70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 71 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 72 |
+
| 0.9469 | 0.1921 | 100 | 0.7808 | 0.1610 |
|
| 73 |
+
| 0.7241 | 0.3842 | 200 | 0.5663 | 0.1597 |
|
| 74 |
+
| 0.5805 | 0.5764 | 300 | 0.4338 | 0.1494 |
|
| 75 |
+
| 0.4717 | 0.7685 | 400 | 0.3221 | 0.1443 |
|
| 76 |
+
| 0.3769 | 0.9606 | 500 | 0.2380 | 0.1488 |
|
| 77 |
+
| 0.3659 | 1.1518 | 600 | 0.2276 | 0.1408 |
|
| 78 |
+
| 0.3316 | 1.3439 | 700 | 0.2139 | 0.1369 |
|
| 79 |
+
| 0.2798 | 1.5360 | 800 | 0.2151 | 0.1308 |
|
| 80 |
+
| 0.3207 | 1.7281 | 900 | 0.2075 | 0.1284 |
|
| 81 |
+
| 0.3199 | 1.9203 | 1000 | 0.2008 | 0.1265 |
|
| 82 |
+
| 0.2722 | 2.1114 | 1100 | 0.2009 | 0.1263 |
|
| 83 |
+
| 0.271 | 2.3036 | 1200 | 0.2077 | 0.1238 |
|
| 84 |
+
| 0.251 | 2.4957 | 1300 | 0.2121 | 0.1237 |
|
| 85 |
+
| 0.2918 | 2.6878 | 1400 | 0.1939 | 0.1224 |
|
| 86 |
+
| 0.2686 | 2.8799 | 1500 | 0.1992 | 0.1221 |
|
| 87 |
+
| 0.2668 | 3.0711 | 1600 | 0.1974 | 0.1226 |
|
| 88 |
+
| 0.2287 | 3.2632 | 1700 | 0.2060 | 0.1201 |
|
| 89 |
+
| 0.2546 | 3.4553 | 1800 | 0.1979 | 0.1200 |
|
| 90 |
+
| 0.2705 | 3.6475 | 1900 | 0.1938 | 0.1220 |
|
| 91 |
+
| 0.2647 | 3.8396 | 2000 | 0.1971 | 0.1205 |
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
### Framework versions
|
| 95 |
+
|
| 96 |
+
- Transformers 4.48.3
|
| 97 |
+
- Pytorch 2.5.1+cu124
|
| 98 |
+
- Datasets 3.3.2
|
| 99 |
+
- Tokenizers 0.21.0
|