S2t Small Librispeech Asr

🚀 S2T-SMALL-LIBRISPEECH-ASR

s2t-small-librispeech-asr is a Speech to Text Transformer (S2T) model designed for automatic speech recognition (ASR). It offers an effective solution for converting spoken language into text, leveraging the power of the Transformer architecture.

🚀 Quick Start

s2t-small-librispeech-asr is a Speech to Text Transformer (S2T) model trained for automatic speech recognition (ASR). The S2T model was proposed in this paper and released in this repository.

✨ Features

• End - to - end ASR: S2T is an end - to - end sequence - to - sequence transformer model. It is trained with standard autoregressive cross - entropy loss and generates the transcripts autoregressively.
• Multiple Datasets Support: Can be evaluated on different subsets of the LibriSpeech dataset, like "clean" and "other".

📦 Installation

To use this model, you need to install some dependencies. You could either install those as extra speech dependancies with pip install transformers"[speech, sentencepiece]" or install the packages separately with pip install torchaudio sentencepiece.

💻 Usage Examples

Basic Usage

import torch
from transformers import Speech2TextProcessor, Speech2TextForConditionalGeneration
from datasets import load_dataset

model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-librispeech-asr")
processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-librispeech-asr")

ds = load_dataset(
    "patrickvonplaten/librispeech_asr_dummy",
    "clean",
    split="validation"
)

input_features = processor(
    ds[0]["audio"]["array"],
    sampling_rate=16_000,
    return_tensors="pt"
).input_features  # Batch size 1
generated_ids = model.generate(input_features=input_features)

transcription = processor.batch_decode(generated_ids)

Advanced Usage

The following script shows how to evaluate this model on the LibriSpeech "clean" and "other" test dataset.

from datasets import load_dataset
from evaluate import load
from transformers import Speech2TextForConditionalGeneration, Speech2TextProcessor

librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")  # change to "other" for other test dataset
wer = load("wer")

model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-librispeech-asr").to("cuda")
processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-librispeech-asr", do_upper_case=True)

def map_to_pred(batch):
    features = processor(batch["audio"]["array"], sampling_rate=16000, padding=True, return_tensors="pt")
    input_features = features.input_features.to("cuda")
    attention_mask = features.attention_mask.to("cuda")

    gen_tokens = model.generate(input_features=input_features, attention_mask=attention_mask)
    batch["transcription"] = processor.batch_decode(gen_tokens, skip_special_tokens=True)[0]
    return batch

result = librispeech_eval.map(map_to_pred, remove_columns=["audio"])

print("WER:", wer.compute(predictions=result["transcription"], references=result["text"]))

Result (WER):

📚 Documentation

Intended uses & limitations

This model can be used for end - to - end speech recognition (ASR). See the model hub to look for other S2T checkpoints.

Model Information

Training procedure

Preprocessing

The speech data is pre - processed by extracting Kaldi - compliant 80 - channel log mel - filter bank features automatically from WAV/FLAC audio files via PyKaldi or torchaudio. Further utterance - level CMVN (cepstral mean and variance normalization) is applied to each example. The texts are lowercased and tokenized using SentencePiece and a vocabulary size of 10,000.

Training

The model is trained with standard autoregressive cross - entropy loss and using SpecAugment. The encoder receives speech features, and the decoder generates the transcripts autoregressively.

BibTeX entry and citation info

@inproceedings{wang2020fairseqs2t,
  title = {fairseq S2T: Fast Speech-to-Text Modeling with fairseq},
  author = {Changhan Wang and Yun Tang and Xutai Ma and Anne Wu and Dmytro Okhonko and Juan Pino},
  booktitle = {Proceedings of the 2020 Conference of the Asian Chapter of the Association for Computational Linguistics (AACL): System Demonstrations},
  year = {2020},
}

📄 License

This project is licensed under the MIT license.