This collection contains extra extra large (XXL) size versions of Fast Conformer-CTC (1B parameters) finetuned on NeMo ASRSet with around 24500 hours of english speech. Model is first pretrained on LibriLight using SSL methods. The model transcribes speech in lower case english alphabet along with spaces and apostrophes.
FastConformer-CTC model is a non-autoregressive variant of Conformer model  for Automatic Speech Recognition which uses CTC loss/decoding instead of Transducer. You may find more info on the detail of this model here: Fast-Conformer Model.
The tokenizers for these models were built using the text transcripts of the train set with this script.
All the models in this collection are trained on a composite dataset (NeMo ASRSET) comprising of several thousand hours of English speech:
- Librispeech 960 hours of English speech
- Fisher Corpus
- Switchboard-1 Dataset
- WSJ-0 and WSJ-1
- National Speech Corpus (Part 1, Part 6)
- VoxPopuli (EN)
- Europarl-ASR (EN)
- Multilingual Librispeech (MLS EN) - 2,000 hours subset
- Mozilla Common Voice (v7.0)
- People's Speech - 12,000 hrs subset
Model is first pretrained on Librilight 60k hrs of data and then finetuned on NeMo ASR Set 3.0
The list of the available models in this collection is shown in the following table. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding.
|NSC Part 1
|MCV Test 7.0
|NeMo ASRSET 3.0
You may use language models to improve the accuracy of the models.
How to Use this Model
The model is available for use in the NeMo toolkit , and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.
Automatically load the model from NGC
import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecCTCModelBPE.from_pretrained(model_name="stt_en_fastconformer_ctc_xxlarge")
Transcribing text with this model
python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py \
audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
This model accepts 16000 KHz Mono-channel Audio (wav files) as input.
This model provides transcribed speech as a string for a given audio sample.
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.