S2t Small Mustc En It St

🚀 S2T-SMALL-MUSTC-EN-IT-ST

s2t-small-mustc-en-it-st is a Speech to Text Transformer (S2T) model for end - to - end Speech Translation (ST), enabling English speech to Italian text translation.

🚀 Quick Start

As this is a standard sequence - to - sequence transformer model, you can use the generate method to generate transcripts by passing speech features to the model.

Note: The Speech2TextProcessor object uses torchaudio to extract the filter bank features. Make sure to install the torchaudio package before running this example.

You could either install those as extra speech dependencies with pip install transformers"[speech, sentencepiece]" or install the packages separately with pip install torchaudio sentencepiece.

import torch
from transformers import Speech2TextProcessor, Speech2TextForConditionalGeneration
from datasets import load_dataset
import soundfile as sf

model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-mustc-en-it-st")
processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-mustc-en-it-st")

def map_to_array(batch):
    speech, _ = sf.read(batch["file"])
    batch["speech"] = speech
    return batch

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

inputs = processor(
    ds["speech"][0],
    sampling_rate=16_000,
    return_tensors="pt"
)
generated_ids = model.generate(input_ids=inputs["input_features"], attention_mask=inputs["attention_mask"])

translation = processor.batch_decode(generated_ids, skip_special_tokens=True)

✨ Features

• End - to - end ST: Capable of performing end - to - end English speech to Italian text translation.
• Transformer - based: Built on a transformer - based seq2seq (encoder - decoder) architecture.
• Pre - processing: Applies feature extraction and normalization techniques to speech data and tokenization to texts.

📦 Installation

You could either install the necessary packages as extra speech dependencies with pip install transformers"[speech, sentencepiece]" or install them separately with pip install torchaudio sentencepiece.

💻 Usage Examples

Basic Usage

import torch
from transformers import Speech2TextProcessor, Speech2TextForConditionalGeneration
from datasets import load_dataset
import soundfile as sf

model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-mustc-en-it-st")
processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-mustc-en-it-st")

def map_to_array(batch):
    speech, _ = sf.read(batch["file"])
    batch["speech"] = speech
    return batch

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

inputs = processor(
    ds["speech"][0],
    sampling_rate=16_000,
    return_tensors="pt"
)
generated_ids = model.generate(input_ids=inputs["input_features"], attention_mask=inputs["attention_mask"])

translation = processor.batch_decode(generated_ids, skip_special_tokens=True)

📚 Documentation

Model description

S2T is a transformer - based seq2seq (encoder - decoder) model designed for end - to - end Automatic Speech Recognition (ASR) and Speech Translation (ST). It uses a convolutional downsampler to reduce the length of speech inputs by 3/4th before they are fed into the encoder. The model is trained with standard autoregressive cross - entropy loss and generates the transcripts/translations autoregressively.

Intended uses & limitations

This model can be used for end - to - end English speech to Italian text translation. See the model hub to look for other S2T checkpoints.

🔧 Technical Details

Training data

The s2t - small - mustc - en - it - st is trained on the English - Italian subset of [MuST - C](https://ict.fbk.eu/must - c/). MuST - C is a multilingual speech translation corpus whose size and quality facilitates the training of end - to - end systems for speech translation from English into several languages. For each target language, MuST - C comprises several hundred hours of audio recordings from English TED Talks, which are automatically aligned at the sentence level with their manual transcriptions and translations.

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 8,000.

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. To accelerate model training and for better performance, the encoder is pre - trained for English ASR.

Evaluation results

MuST - C test results for en - it (BLEU score): 22.7

📄 License

This project is licensed under the MIT license.

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},
}

⚠️ Important Note

The Speech2TextProcessor object uses torchaudio to extract the filter bank features. Make sure to install the torchaudio package before running the usage example.

💡 Usage Tip

You could either install the necessary packages as extra speech dependencies with pip install transformers"[speech, sentencepiece]" or install them separately with pip install torchaudio sentencepiece.