|
--- |
|
license: apache-2.0 |
|
base_model: imvladikon/whisper-medium-he |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: whisper-medium-he |
|
results: [] |
|
language: |
|
- he |
|
pipeline_tag: automatic-speech-recognition |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# whisper-medium-he[WIP] |
|
|
|
This model is a fine-tuned version of [imvladikon/whisper-medium-he](https://huggingface.co./imvladikon/whisper-medium-he) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2061 |
|
- Wer: 13.4020 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 1e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 2 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- training_steps: 4000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
| 0.0983 | 0.1 | 1000 | 0.3072 | 16.4362 | |
|
| 0.1219 | 0.2 | 2000 | 0.2923 | 15.6642 | |
|
| 0.134 | 0.3 | 3000 | 0.2345 | 13.7450 | |
|
| 0.2113 | 0.39 | 4000 | 0.2061 | 13.4020 | |
|
|
|
|
|
### Inference |
|
|
|
#### HF |
|
|
|
```python |
|
from transformers import pipeline |
|
pipe = pipeline("automatic-speech-recognition", model="imvladikon/whisper-medium-he", device_map="auto") # requires `pip install accelerate` |
|
print(recognize("sample.mp3")) |
|
``` |
|
|
|
#### whisper.cpp |
|
|
|
Prepared : https://huggingface.co./imvladikon/whisper-medium-he/blob/main/ggml-hebrew.bin |
|
|
|
But if need to convert: |
|
```bash |
|
git clone https://github.com/openai/whisper |
|
git clone https://github.com/ggerganov/whisper.cpp |
|
git clone https://huggingface.co./imvladikon/whisper-medium-he |
|
python3 ./whisper.cpp/models/convert-h5-to-ggml.py ./whisper-medium-he/ ./whisper . |
|
``` |
|
|
|
Then possible to check (if produced model is `ggml-model.bin`): |
|
```bash |
|
cd whisper.cpp && ./main -m ../ggml-model.bin -f ../sample.wav |
|
``` |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
