README.md

---
license: cc-by-nc-4.0
language: ca
tags:
- audio
- automatic-speech-recognition
- whisper-large-v3
- projecte-aina
- barcelona-supercomputing-center
model-index:
- name: CLiC-UB/faster-whisper-large-v3-ca-rapnic-paralysis-full
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Rapnic (Test)
      type: CLiC-UB/rapnic-example
      split: test
      args:
        language: ca
    metrics:
    - name: WER
      type: wer
      value: 27.49
base_model:
- BSC-LT/whisper-large-v3-ca-punctuated-3370h
pipeline_tag: automatic-speech-recognition
library_name: transformers
---
# faster-whisper-large-v3-ca-rapnic-paralysis-full

## Table of Contents
<details>
<summary>Click to expand</summary>

- [faster-whisper-large-v3-ca-rapnic-paralysis-full](#faster-whisper-large-v3-ca-rapnic-paralysis-full)
  - [Table of Contents](#table-of-contents)
  - [Model Description](#model-description)
  - [How to Get Started with the Model](#how-to-get-started-with-the-model)
    - [Installation](#installation)
    - [For Inference](#for-inference)
  - [Conversion Details](#conversion-details)
    - [Conversion procedure](#conversion-procedure)
  - [Additional Information](#additional-information)
    - [Contact](#contact)
    - [License](#license)

</details>

## Model Description
Faster Whisper conversion of [CLiC-UB/whisper-large-v3-ca-rapnic-paralysis-full](https://huggingface.co/CLiC-UB/whisper-large-v3-ca-rapnic-paralysis-full)


## How to Get Started with the Model

### Installation

To use this model, you may install [faster-whisper](https://github.com/guillaumekln/faster-whisper/tree/master) 

Create a virtual environment:
```bash
python -m venv /path/to/venv
```
Activate the environment:
```bash
source /path/to/venv/bin/activate
```
Install the modules:
```bash
pip install faster-whisper
```

### For Inference
To transcribe audio in Catalan using this model, you can follow this example:

```python
from faster_whisper import WhisperModel

model_size = "CLiC-UB/faster-whisper-large-v3-ca-rapnic-paralysis-full"

# Run on GPU with FP16
model = WhisperModel(model_size, device="cuda", compute_type="float16")

# or run on GPU with INT8
#model = WhisperModel(model_size, device="cuda", compute_type="int8_float16")
# or run on CPU with INT8
# model = WhisperModel(model_size, device="cpu", compute_type="int8")

segments, info = model.transcribe("audio_in_catalan.mp3", beam_size=5, task="transcribe",language="ca")

print("Detected language '%s' with probability %f" % (info.language, info.language_probability))

for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
```

## Conversion Details

### Conversion procedure

This model is not a direct result of training. It is a conversion of a [Whisper](https://huggingface.co/openai/whisper-large-v3) model using [faster-whisper](https://github.com/guillaumekln/faster-whisper/tree/master). The procedure to create the model is as follows:

```bash
ct2-transformers-converter --model CLiC-UB/whisper-large-v3-ca-rapnic-paralysis-full
   --output_dir faster-whisper-large-v3-ca-rapnic-paralysis-full
   --copy_files preprocessor_config.json tokenizer.json
```

## Additional Information

### Contact
For further information, please send an email to <gr.clic@ub.edu>.

### License

[CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/deed.en)