This collection contains Self-Supervised Learning (SSL) checkpoints for xlarge size versions of Conformer model (around 0.6B parameters). Models are trained using unlabeled english audio with contrastive loss. These are similar to w2v-Conformer XL [3,4] and can be fine-tuned for Automatic Speech Recognition (ASR).
For details about conformer architecture, refer to .
The NeMo toolkit  was used for training the models. These model are trained with this example script and this base config.
All the models in this collection are trained using LibriLight corpus (~56k hrs of unlabeled English speech).
The pre-trained checkpoints are available in NeMo toolkit , and has to be fine-tuned on another labeled dataset for ASR.
import nemo.collections.asr as nemo_asr ssl_model = nemo_asr.models.ssl_models.SpeechEncDecSelfSupervisedModel.from_pretrained(model_name='ssl_en_conformer_xlarge')
To continue ssl training on your own dataset, set
optim in config appropriately and use the script.
To fine-tune using a labeled dataset, refer to this example script for transducer loss and to this example script for using CTC loss.
Briefly, you can load the pre-trained checkpoint into fine-tune model as shown below
# define fine-tune model asr_model = nemo_asr.models.EncDecRNNTBPEModel(cfg=cfg.model, trainer=trainer) # load ssl checkpoint asr_model.load_state_dict(ssl_model.state_dict(), strict=False) del ssl_model
The list of the available models in this collection is shown in the following table. Performances of the ASR models fine-tuned from these check-points are reported in terms of Word Error Rate (WER%) with greedy decoding.
|Version||SSL Loss||Fine-tune Dataset||Fine-tune Model||Vocabulary Size||LS dev-clean||LS dev-other||LS test-clean||LS test-other|
Since this model was trained on publically available speech datasets, the performance of this model might degrade for speech which includes technical terms, or vernacular that the model has not been trained on. The model might also perform worse for accented speech.
 Conformer: Convolution-augmented Transformer for Speech Recognition
 Pushing the Limits of SSL for ASR
 W2V-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-training