Gigaam Ctc

🚀 GigaAM-v2-CTC 🤗 Hugging Face transformers

Russian ASR model GigaAM-v2-CTC, offering an efficient solution for automatic speech recognition tasks.

🚀 Quick Start

Russian ASR model GigaAM-v2-CTC. You can start using it following the steps below.

✨ Features

• This is an original GigaAM-v2-CTC with transformers library interface.
• File gigaam_transformers.py contains model, feature extractor and tokenizer classes with usual transformers methods. Model can be initialized with transformers auto classes.

📦 Installation

The required library versions are as follows:

• torch 2.5.1
• torchaudio 2.5.1
• transformers 4.49.0
• accelerate 1.5.2

💻 Usage Examples

Basic Usage

from transformers import AutoModel, AutoProcessor
import torch
import torchaudio

# load audio
wav, sr = torchaudio.load("audio.wav")
# resample if necessary
wav = torchaudio.functional.resample(wav, sr, 16000)

# load model and processor
processor = AutoProcessor.from_pretrained("waveletdeboshir/gigaam-ctc", trust_remote_code=True)
model = AutoModel.from_pretrained("waveletdeboshir/gigaam-ctc", trust_remote_code=True)
model.eval()

input_features = processor(wav[0], sampling_rate=16000, return_tensors="pt")

# predict
with torch.no_grad():
    logits = model(**input_features).logits
# greedy decoding
greedy_ids = logits.argmax(dim=-1)
# decode token ids to text
transcription = processor.batch_decode(greedy_ids)[0]

📚 Documentation

Fine-tune

You can fine-tune the model using the following links:

• 
• Fine-tuning Jupyter

📄 License

This project is under the MIT license.