Edit model card

NVIDIA Conformer-Transducer Large (es)

| Model architecture | Model size | Language

This model transcribes speech in lowercase Spanish alphabet including spaces, and was trained on a composite dataset comprising of 1340 hours of Spanish speech. It is a "large" variant of Conformer-Transducer, with around 120 million parameters. 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 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
asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained("nvidia/stt_es_conformer_transducer_large")

Transcribing using Python

First, let's get a sample

wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav

Then simply do:


Transcribing many audio files

python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py 


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


This model provides transcribed speech as a string for a given audio sample.

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.


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.


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


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 MCV 7.0 Dev MCV 7.0 Test MLS Dev MLS Test Voxpopuli Dev Voxpopuli Test Fisher Dev Fisher Test Train Dataset
1.8.0 SentencePiece Unigram 1024 4.6 5.2 2.7 3.2 4.7 6.0 14.7 14.8 NeMo ASRSET 2.0


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



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.

Downloads last month
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Datasets used to train nvidia/stt_es_conformer_transducer_large

Evaluation results