transformers/docs/source/en/model_doc/wav2vec2-bert.md

Wav2Vec2-BERT

Overview

The Wav2Vec2-BERT model was proposed in Seamless: Multilingual Expressive and Streaming Speech Translation by the Seamless Communication team from Meta AI.

This model was pre-trained on 4.5M hours of unlabeled audio data covering more than 143 languages. It requires finetuning to be used for downstream tasks such as Automatic Speech Recognition (ASR), or Audio Classification.

The official results of the model can be found in Section 3.2.1 of the paper.

The abstract from the paper is the following:

Recent advancements in automatic speech translation have dramatically expanded language coverage, improved multimodal capabilities, and enabled a wide range of tasks and functionalities. That said, large-scale automatic speech translation systems today lack key features that help machine-mediated communication feel seamless when compared to human-to-human dialogue. In this work, we introduce a family of models that enable end-to-end expressive and multilingual translations in a streaming fashion. First, we contribute an improved version of the massively multilingual and multimodal SeamlessM4T model—SeamlessM4T v2. This newer model, incorporating an updated UnitY2 framework, was trained on more low-resource language data. The expanded version of SeamlessAlign adds 114,800 hours of automatically aligned data for a total of 76 languages. SeamlessM4T v2 provides the foundation on which our two newest models, SeamlessExpressive and SeamlessStreaming, are initiated. SeamlessExpressive enables translation that preserves vocal styles and prosody. Compared to previous efforts in expressive speech research, our work addresses certain underexplored aspects of prosody, such as speech rate and pauses, while also preserving the style of one’s voice. As for SeamlessStreaming, our model leverages the Efficient Monotonic Multihead Attention (EMMA) mechanism to generate low-latency target translations without waiting for complete source utterances. As the first of its kind, SeamlessStreaming enables simultaneous speech-to-speech/text translation for multiple source and target languages. To understand the performance of these models, we combined novel and modified versions of existing automatic metrics to evaluate prosody, latency, and robustness. For human evaluations, we adapted existing protocols tailored for measuring the most relevant attributes in the preservation of meaning, naturalness, and expressivity. To ensure that our models can be used safely and responsibly, we implemented the first known red-teaming effort for multimodal machine translation, a system for the detection and mitigation of added toxicity, a systematic evaluation of gender bias, and an inaudible localized watermarking mechanism designed to dampen the impact of deepfakes. Consequently, we bring major components from SeamlessExpressive and SeamlessStreaming together to form Seamless, the first publicly available system that unlocks expressive cross-lingual communication in real-time. In sum, Seamless gives us a pivotal look at the technical foundation needed to turn the Universal Speech Translator from a science fiction concept into a real-world technology. Finally, contributions in this work—including models, code, and a watermark detector—are publicly released and accessible at the link below.

This model was contributed by ylacombe. The original code can be found here.

Usage tips

• Wav2Vec2-BERT follows the same architecture as Wav2Vec2-Conformer, but employs a causal depthwise convolutional layer and uses as input a mel-spectrogram representation of the audio instead of the raw waveform.
• Wav2Vec2-BERT can use either no relative position embeddings, Shaw-like position embeddings, Transformer-XL-like position embeddings, or rotary position embeddings by setting the correct config.position_embeddings_type.
• Wav2Vec2-BERT also introduces a Conformer-based adapter network instead of a simple convolutional network.

Resources

• [Wav2Vec2BertForCTC] is supported by this example script.
• You can also adapt these notebooks on how to finetune a speech recognition model in English, and how to finetune a speech recognition model in any language.

• [Wav2Vec2BertForSequenceClassification] can be used by adapting this example script.
• See also: Audio classification task guide

Wav2Vec2BertConfig

autodoc Wav2Vec2BertConfig

Wav2Vec2BertProcessor

autodoc Wav2Vec2BertProcessor - call - pad - from_pretrained - save_pretrained - batch_decode - decode

Wav2Vec2BertModel

autodoc Wav2Vec2BertModel - forward

Wav2Vec2BertForCTC

autodoc Wav2Vec2BertForCTC - forward

Wav2Vec2BertForSequenceClassification

autodoc Wav2Vec2BertForSequenceClassification - forward

Wav2Vec2BertForAudioFrameClassification

autodoc Wav2Vec2BertForAudioFrameClassification - forward

Wav2Vec2BertForXVector

autodoc Wav2Vec2BertForXVector - forward