Whisper Large Pt Cv11

🚀 Whisper Large Portuguese

This model is a fine - tuned version of openai/whisper-large-v2 on Portuguese, aiming to enhance automatic speech recognition performance in the Portuguese language.

🚀 Quick Start

✨ Features

• This is a fine - tuned model of openai/whisper-large-v2 on Portuguese.
• It uses the train and validation splits of Common Voice 11.
• Supports multiple evaluation scenarios, including raw text and normalized text.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import pipeline

transcriber = pipeline(
  "automatic-speech-recognition", 
  model="jonatasgrosman/whisper-large-pt-cv11"
)

transcriber.model.config.forced_decoder_ids = (
  transcriber.tokenizer.get_decoder_prompt_ids(
    language="pt", 
    task="transcribe"
  )
)

transcription = transcriber("path/to/my_audio.wav")

📚 Documentation

Evaluation

The model evaluation was performed using the test split of two datasets: Common Voice 11 (the same dataset used for fine - tuning) and Fleurs (a dataset not seen during fine - tuning).

Since Whisper can transcribe casing and punctuation, the model evaluation was carried out in two different scenarios: one using raw text and the other using normalized text (lowercase + removal of punctuations). Additionally, for the Fleurs dataset, the model was evaluated in a scenario where there are no transcriptions of numerical values, as the way these values are described in this dataset is different from how they are described in the fine - tuning dataset (Common Voice).

Common Voice 11

Fleurs

📄 License

The model is licensed under the Apache - 2.0 license.

Other Information