---
license: apache-2.0
pipeline_tag: automatic-speech-recognition
tags:
- pytorch
---
## Versions:

- CUDA: 12.1
- cuDNN Version: 8.9.2.26_1.0-1_amd64

* tensorflow Version: 2.12.0
* torch Version: 2.1.0.dev20230606+cu12135
* transformers Version: 4.30.2
* accelerate Version: 0.20.3

## BENCHMARK:

- RAM: 2.8 GB (Original_Model: 5.5GB)
- VRAM: 1812 MB (Original_Model: 6GB)
- test.wav: 23 s (Multilingual Speech i.e. English+Hindi)

  | Device Name       | float32 (Original)   | float16 | CudaCores | TensorCores |
  | ----------------- | -------------------- | ------- | --------- | ----------- |
  | 3060              | 1.7                  | 1.1     | 3,584     | 112         |
  | 1660 Super        | OOM                  | 3.3     | 1,408     | -           |
  | Collab (Tesla T4) | 2.8                  | 2.2     | 2,560     | 320         |
  | Collab (CPU)      | 35                   | -       | -         | -           |


  - CPU -> torch.float16 not supported on CPU (AMD Ryzen 5 3600 or Collab GPU)
- Punchuation: True

## Usage

A file ``__init__.py`` is contained inside this repo which contains all the code to use this model.

Firstly, clone this repo and place all the files inside a folder.

**Please try in jupyter notebook**

```python
# Import the Model
from whisper_medium_fp16_transformers import Model
```

```python
# Initilise the model
model = Model(
            model_name_or_path='whisper_medium_fp16_transformers',
            cuda_visible_device="0", 
            device='cuda',
      )
```

```python
# Load Audio
audio = model.load_audio('test.wav')
```

```python
# Transcribe (First transcription takes time.)
model.transcribe(audio)
```