S2t Wav2vec2 Large En Ca

🚀 S2T2-Wav2Vec2-CoVoST2-EN-CA-ST

s2t-wav2vec2-large-en-ca is a Speech to Text Transformer model trained for end-to-end Speech Translation (ST). This model addresses the need for seamless conversion from English speech to Catalan text, offering high - efficiency and accurate translation capabilities.

🚀 Quick Start

This model can be used for end-to-end English speech to Catalan text translation. You can use the model directly via the ASR pipeline or step - by - step as shown in the usage examples below.

✨ Features

• End - to - End ST: Trained for end - to - end Speech Translation, enabling direct conversion from English speech to Catalan text.
• Transformer - Based: Utilizes a transformer - based seq2seq (speech encoder - decoder) architecture for efficient processing.
• Pretrained Encoder: Employs a pretrained Wav2Vec2 as the encoder, enhancing performance.

💻 Usage Examples

Basic Usage

from datasets import load_dataset
from transformers import pipeline

librispeech_en = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
asr = pipeline("automatic-speech-recognition", model="facebook/s2t-wav2vec2-large-en-ca", feature_extractor="facebook/s2t-wav2vec2-large-en-ca")

translation = asr(librispeech_en[0]["file"])

Advanced Usage

import torch
from transformers import Speech2Text2Processor, SpeechEncoderDecoder
from datasets import load_dataset

import soundfile as sf
model = SpeechEncoderDecoder.from_pretrained("facebook/s2t-wav2vec2-large-en-ca")
processor = Speech2Text2Processor.from_pretrained("facebook/s2t-wav2vec2-large-en-ca")

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"])
transcription = processor.batch_decode(generated_ids)

📚 Documentation

Model description

S2T2 is a transformer - based seq2seq (speech encoder - decoder) model designed for end - to - end Automatic Speech Recognition (ASR) and Speech Translation (ST). It uses a pretrained Wav2Vec2 as the encoder and a transformer - based decoder. The model is trained with standard autoregressive cross - entropy loss and generates the translations autoregressively.

Intended uses & limitations

This model can be used for end - to - end English speech to Catalan text translation. See the model hub to look for other S2T2 checkpoints.

Evaluation results

CoVoST - V2 test results for en - ca (BLEU score): 34.1

For more information, please have a look at the official paper - especially row 10 of Table 2.

BibTeX entry and citation info

@article{DBLP:journals/corr/abs-2104-06678,
  author    = {Changhan Wang and
               Anne Wu and
               Juan Miguel Pino and
               Alexei Baevski and
               Michael Auli and
               Alexis Conneau},
  title     = {Large-Scale Self- and Semi-Supervised Learning for Speech Translation},
  journal   = {CoRR},
  volume    = {abs/2104.06678},
  year      = {2021},
  url       = {https://arxiv.org/abs/2104.06678},
  archivePrefix = {arXiv},
  eprint    = {2104.06678},
  timestamp = {Thu, 12 Aug 2021 15:37:06 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2104-06678.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

📄 License

This model is released under the MIT license.

Additional Information

Widget Examples

• Common Voice 1: Audio
• Common Voice 2: Audio
• Common Voice 3: Audio