Monsoon Whisper Medium Gigaspeech2

🚀 Monsoon-Whisper-Medium-Gigaspeech2

Monsoon-Whisper-Medium-Gigaspeech2 is a 🇹🇭 Thai Automatic Speech Recognition (ASR) model. It's built upon Whisper-Medium and fine - tuned on GigaSpeech2. Originally developed as a scale experiment for research on emergent capabilities in ASR tasks, it performs well in real - world scenarios, including with YouTube - sourced audio and in noisy environments. More details can be found in our Typhoon - Audio Release Blog.

🚀 Quick Start

Monsoon - Whisper - Medium - Gigaspeech2 is a Thai ASR model based on Whisper - Medium and fine - tuned on GigaSpeech2. It's suitable for various ASR tasks, especially in real - world and noisy environments.

✨ Features

• Based on the well - known Whisper - Medium architecture.
• Fine - tuned on GigaSpeech2 for better performance on Thai speech recognition.
• Performs well in real - world scenarios, including with YouTube audio and in noisy environments.

📦 Installation

The model requires transformers 4.38.0 or newer. You can install it using pip:

pip install transformers>=4.38.0

💻 Usage Examples

Basic Usage

from transformers import WhisperProcessor, WhisperForConditionalGeneration
import torchaudio
import torch

model_path = "scb10x/monsoon-whisper-medium-gigaspeech2"
device = "cuda"
filepath = 'audio.wav'

processor = WhisperProcessor.from_pretrained(model_path)
model = WhisperForConditionalGeneration.from_pretrained(
    model_path, torch_dtype=torch.bfloat16
)
model.to(device)
model.eval()

model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(
    language="th", task="transcribe"
)
array, sr = torchaudio.load(filepath)
input_features = (
    processor(array, sampling_rate=sr, return_tensors="pt")
    .to(device)
    .to(torch.bfloat16)
    .input_features
)
predicted_ids = model.generate(input_features)
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
print(transcription)

📚 Documentation

Model Description

Evaluation Results

Intended Uses & Limitations

⚠️ Important Note

This model is experimental and may not always be accurate. Developers should carefully assess potential risks in the context of their specific applications.

🔗 Follow us & Support

• Twitter
• Discord

👥 Typhoon Team

Kunat Pipatanakul, Potsawee Manakul, Sittipong Sripaisarnmongkol, Natapong Nitarach, Warit Sirichotedumrong, Adisai Na - Thalang, Phatrasek Jirabovonvisut, Parinthapat Pengpun, Krisanapong Jirayoot, Pathomporn Chokchainant, Kasima Tharnpipitchai

📄 License

This model is licensed under the Apache 2.0 license.