pgwi/en_pt_titanet_large

NVIDIA TitaNet-Large (PT)

| | |

This model extracts speaker embeddings from given speech, which is the backbone for speaker verification and diarization tasks. It is a "large" version of TitaNet (around 23M parameters) models.
See the model architecture section and NeMo documentation for complete architecture details.

NVIDIA NeMo: Training

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 the latest Pytorch version.

pip install nemo_toolkit['all']

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 instantiate the model

import nemo.collections.asr as nemo_asr
speaker_model = nemo_asr.models.EncDecSpeakerLabelModel.restore_from("./titanet_finetune_pt.nemo")

Embedding Extraction

Using

emb = speaker_model.get_embedding("an255-fash-b.wav")

Verifying two utterances (Speaker Verification)

Now to check if two audio files are from the same speaker or not, simply do:

speaker_model.verify_speakers("an255-fash-b.wav","cen7-fash-b.wav")

Extracting Embeddings for more audio files

To extract embeddings from a bunch of audio files:

Write audio files to a manifest.json file with lines as in format:

{"audio_filepath": "<absolute path to dataset>/audio_file.wav", "duration": "duration of file in sec", "label": "speaker_id"}

Then running following script will extract embeddings and writes to current working directory:

python <NeMo_root>/examples/speaker_tasks/recognition/extract_speaker_embeddings.py --manifest=manifest.json

Input

This model accepts 16000 KHz Mono-channel Audio (wav files) as input.

Output

This model provides speaker embeddings for an audio file.

Model Architecture

TitaNet model is a depth-wise separable conv1D model [1] for Speaker Verification and diarization tasks. You may find more info on the detail of this model here: TitaNet-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.

Datasets

All the models in this collection are trained on a composite dataset comprising several thousand hours of English speech:

• common voice (pt)

Performance

Performances of the these models are reported in terms of Equal Error Rate (EER%) on speaker verification evaluation trial files.

• Speaker Verification (EER%)

  Version	Model	Model Size	Common Voice(Turkish)
  1.10.0	TitaNet-Large	23M	TODO

Limitations

This model is trained on both telephonic and non-telephonic speech from voxceleb datasets, Fisher and switch board. If your domain of data differs from trained data or doesnot show relatively good performance consider finetuning for that speech domain.

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 isn’t supported yet by Riva, the list of supported models is here.
Check out Riva live demo.

References

[1] TitaNet: Neural Model for Speaker Representation with 1D Depth-wise Separable convolutions and global context [2] NVIDIA NeMo Toolkit

Licence

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.