Stt Es Conformer Ctc Large

🚀 NVIDIA Conformer-CTC Large (es)

This model is designed to transcribe Spanish speech. It can handle lowercase Spanish alphabet including spaces. Trained on a composite dataset of 1340 hours of Spanish speech, it's a non - autoregressive "large" Conformer variant with around 120 million parameters. It's also compatible with NVIDIA Riva for production - grade server deployments.

| | | | |

🚀 Quick Start

This model can be used in the NeMo toolkit. You can use it as a pre - trained checkpoint for inference or fine - tuning on another dataset.

To train, fine - tune or play with the model, you need to install NVIDIA NeMo. We recommend installing it after the latest PyTorch version.

pip install nemo_toolkit['all']

✨ Features

• Transcribes Spanish speech in lowercase with spaces.
• Non - autoregressive "large" Conformer variant with about 120 million parameters.
• Compatible with NVIDIA Riva for production - grade server deployments.

📦 Installation

To use this model, you first need to install the NeMo toolkit.

pip install nemo_toolkit['all']

💻 Usage Examples

Basic Usage

Automatically instantiate the model:

import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecCTCModelBPE.from_pretrained("nvidia/stt_es_conformer_ctc_large")

Advanced Usage

Transcribing using Python

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_es_conformer_ctc_large" 
 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.

📚 Documentation

Model Architecture

Conformer - CTC model is a non - autoregressive variant of Conformer model [1] for Automatic Speech Recognition which uses CTC loss/decoding instead of Transducer. You may find more info on the detail of this model here: Conformer - CTC 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.

The checkpoint of the language model used as the neural rescorer can be found here. You may find more info on how to train and use language models for ASR models here: ASR Language Modeling

Datasets

All the models in this collection are trained on a composite dataset (NeMo ASRSET) comprising of 1340 hours of Spanish speech:

• Mozilla Common Voice 7.0 (Spanish) - 289 hours after data cleaning
• Multilingual LibriSpeech (Spanish) - 801 hours after data cleaning
• Voxpopuli transcribed subset (Spanish) - 110 hours after data cleaning
• Fisher dataset (Spanish) - 140 hours after data cleaning

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.

While deploying with NVIDIA Riva, you can combine this model with external language models to further improve WER. The WER(%) of the latest model with different language modeling techniques are reported in the following table.

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.

Deployment with NVIDIA Riva

For the best real - time accuracy, latency, and throughput, deploy the model with NVIDIA Riva, an accelerated speech AI SDK deployable on - prem, in all clouds, multi - cloud, hybrid, at the 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 Check out Riva live demo.

🔧 Technical Details

This model is a non - autoregressive "large" variant of Conformer, with around 120 million parameters. It uses CTC loss/decoding instead of Transducer for Automatic Speech Recognition.

📄 License

This model is licensed under cc - by - 4.0.

References

• [1] Conformer: Convolution - augmented Transformer for Speech Recognition
• [2] Google Sentencepiece Tokenizer
• [3] NVIDIA NeMo Toolkit