Stt De Conformer Transducer Large

🚀 NVIDIA Conformer-Transducer Large (de)

This model is designed for automatic speech recognition in German, leveraging the Conformer-Transducer architecture to achieve high - quality transcription.

🚀 Quick Start

Installation

To train, fine - tune or play with the model, you need to install NVIDIA NeMo. It is recommended to install it after installing the latest Pytorch version.

pip install nemo_toolkit['all']

Usage

Automatically instantiate the model

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

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_de_conformer_transducer_large" 
 audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"

✨ Features

• Model Architecture: The Conformer - Transducer model is an autoregressive variant of the Conformer model for Automatic Speech Recognition, using Transducer loss/decoding instead of CTC Loss. More details can be found here: Conformer - Transducer Model.
• Input: Accepts 16000 KHz Mono - channel Audio (wav files) as input.
• Output: Provides transcribed speech as a string for a given audio sample.

📦 Installation

The installation command for using the model is as follows:

pip install nemo_toolkit['all']

💻 Usage Examples

Basic Usage

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

Advanced Usage

Transcribing a single audio file

import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained("nvidia/stt_de_conformer_transducer_large")
output = asr_model.transcribe(['2086-149220-0033.wav'])
print(output[0].text)

Transcribing multiple audio files

python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py 
 pretrained_name="nvidia/stt_de_conformer_transducer_large" 
 audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"

📚 Documentation

Model Architecture

The Conformer - Transducer model is an autoregressive variant of the Conformer model [1] for Automatic Speech Recognition, which uses Transducer loss/decoding instead of CTC Loss. You can find more information about this model here: Conformer - Transducer Model.

Training

The NeMo toolkit [3] was used for training the models for over several hundred epochs. These models 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 German speech:

• VoxPopuli (DE) 200 hrs subset
• Multilingual Librispeech (MLS DE) - 1500 hrs subset
• Mozilla Common Voice (v7.0)

Note: older versions of the model may have trained on a 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.

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

🔧 Technical Details

The model uses the Conformer - Transducer architecture for Automatic Speech Recognition. It is an autoregressive variant of the Conformer model, replacing CTC Loss with Transducer loss/decoding. The NeMo toolkit was used for training over several hundred epochs, with specific example scripts and base configurations. The tokenizers were built using text transcripts of the training set.

📄 License

The 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