STT En Conformer-Transducer Large
Model Overview
This collection contains large size versions of Conformer-Transducer (around 120M parameters) trained on NeMo ASRSet with around 24000 hours of english speech. The model transcribes speech in lower case english alphabet along with spaces and apostrophes.
Model Architecture
Conformer-Transducer model is an autoregressive variant of Conformer model [1] for Automatic Speech Recognition which uses Transducer loss/decoding. You may find more info on the detail of this model here: Conformer-Transducer Model.
Training
The NeMo toolkit [3] was used for training the models. These model are trained with this example script and this base config.
The tokenizers for these models were built using the text transcripts of the train set with this script.
Datasets
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)
- VCTK
- 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
Note: older versions of the model may have trained on smaller set of datasets.
Performance
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.
| Version | Tokenizer | Vocabulary Size | LS test-other | LS test-clean | WSJ Eval92 | WSJ Dev93 | NSC Part 1 | MLS Test | MCV Test 6.1 | MCV Test 8.0 | Train Dataset |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.10.0 | SentencePiece Unigram | 1024 | 3.7 | 1.7 | 1.5 | 2.1 | 5.9 | 5.8 | 6.5 | 7.8 | NeMo ASRSET 3.0 |
| 1.6.0 | SentencePiece Unigram | 1024 | 3.6 | 1.7 | 1.2 | 2.1 | 5.8 | 5.8 | 7.7 | 8.2 | NeMo ASRSET 2.0 |
| 1.4.0 | SentencePiece Unigram | 1024 | 4.3 | 1.9 | 1.5 | 2.5 | 7.8 | - | - | - | NeMo ASRSET 1.4.1 |
How to Use this Model
The model is available for use in the NeMo toolkit [3], 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.EncDecRNNTBPEModel.from_pretrained(model_name="stt_en_conformer_transducer_large")
Transcribing text with this model
python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py \
pretrained_name="stt_en_conformer_transducer_large" \
audio_dir="PATH_TO_AUDIO_FILES"
Input
This model accepts 16000 KHz Mono-channel Audio (wav files) as input.
Output
This model provides transcribed speech as a string for a given audio sample.
Limitations
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.
References
[1] Conformer: Convolution-augmented Transformer for Speech Recognition
[2] Google Sentencepiece Tokenizer
Licence
License to use this model is covered by the NGC TERMS OF USE unless another License/Terms Of Use/EULA is clearly specified. By downloading the public and release version of the model, you accept the terms and conditions of the NGC TERMS OF USE.