Stt De Conformer Ctc Large

🚀 NVIDIA Conformer-CTC Large (de)

This model transcribes German speech and is trained on thousands of hours of German speech data. It's a large - scale Conformer - CTC model with about 120 million parameters and is compatible with NVIDIA Riva for production - grade deployments.

🚀 Quick Start

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.

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']

✨ Features

• Transcribes speech in lowercase German alphabet including spaces.
• A non - autoregressive "large" variant of Conformer with around 120 million parameters.
• Compatible with NVIDIA Riva for production - grade server deployments.

📦 Installation

To use this model, you need to install the NeMo toolkit. You can install it using the following command:

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_de_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_de_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.

Datasets

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

• VoxPopuli (DE)
• Multilingual Librispeech (MLS DE) - 1500 hours 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.

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

The Conformer - CTC model is a non - autoregressive variant for Automatic Speech Recognition. It uses CTC loss/decoding instead of Transducer. The model is trained using the NeMo toolkit for hundreds of epochs with specific scripts and configurations. The tokenizers are built from the text transcripts of the training set.

📄 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