๐ NVIDIA Conformer-Transducer X-Large (en-US)
This model is an "extra-large" Conformer-Transducer model (around 600M parameters) that transcribes English speech, providing transcribed text as output.
๐ Quick Start
This model transcribes speech in lower case English alphabet along with spaces and apostrophes. It is an "extra-large" version of Conformer-Transducer (around 600M parameters) model. See the model architecture section and NeMo documentation for complete architecture details.
|
|
| 
โจ Features
- Transcribes English speech in lower case with spaces and apostrophes.
- An "extra-large" Conformer-Transducer model with around 600M parameters.
- Can be used for inference or fine - tuning in the NeMo toolkit.
๐ฆ Installation
To train, fine-tune or play with the model you will need to install NVIDIA NeMo. We recommend you install it after you've installed latest Pytorch version.
pip install nemo_toolkit['all']
'''
'''
(if it causes an error):
pip install nemo_toolkit[all]
๐ป Usage Examples
Basic Usage
import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained("nvidia/stt_en_conformer_transducer_xlarge")
Advanced Usage
Transcribing a single audio file
First, get a sample:
wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav
Then simply do:
output = asr_model.transcribe(['2086-149220-0033.wav'])
print(output[0].text)
Transcribing many audio files
python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
pretrained_name="nvidia/stt_en_conformer_transducer_xlarge"
audio_dir="<DIRECTORY CONTAINING 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.
๐ Documentation
Model Architecture
Conformer-Transducer model is an autoregressive variant of Conformer model [1] for Automatic Speech Recognition which uses Transducer loss/decoding instead of CTC Loss. 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 for over several hundred epochs. 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 hrs subset
- Mozilla Common Voice (v8.0)
- 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 |
MLS Dev |
MCV Test 8.0 |
Train Dataset |
1.10.0 |
SentencePiece Unigram |
1024 |
3.01 |
1.62 |
1.17 |
2.05 |
5.70 |
5.32 |
4.59 |
6.46 |
NeMo ASRSET 3.0 |
Limitations
Since this model was trained on publicly 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.
NVIDIA Riva: Deployment
NVIDIA Riva, is an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, on edge, and embedded.
Additionally, Riva provides:
- World-class out-of-the-box accuracy for the most common languages with model checkpoints trained on proprietary data with hundreds of thousands of GPU-compute hours
- Best in class accuracy with run-time word boosting (e.g., brand and product names) and customization of acoustic model, language model, and inverse text normalization
- Streaming speech recognition, Kubernetes compatible scaling, and enterprise-grade support
Although this model isnโt supported yet by Riva, the list of supported models is here.
Check out Riva live demo.
๐ง Technical Details
The Conformer-Transducer model uses Transducer loss/decoding instead of CTC Loss in the Conformer architecture for Automatic Speech Recognition. It is trained using the NeMo toolkit for hundreds of epochs with specific example scripts and base configs. The tokenizers are built from the text transcripts of the train set.
๐ License
License to use this model is covered by the CC-BY-4.0. By downloading the public and release version of the model, you accept the terms and conditions of the CC-BY-4.0 license.
References
[1] Conformer: Convolution-augmented Transformer for Speech Recognition
[2] Google Sentencepiece Tokenizer
[3] NVIDIA NeMo Toolkit