NVIDIA Conformer-CTC Large (de)
This model transcribes speech in lowercase German alphabet including spaces, and is trained on several thousand hours of German speech data. It is a non-autoregressive "large" variant of Conformer, with around 120 million parameters. See the model architecture section and NeMo documentation for complete architecture details. It is also compatible with NVIDIA Riva for production-grade server deployments.
Usage
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 latest PyTorch version.
pip install nemo_toolkit['all']
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")
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:
asr_model.transcribe(['2086-149220-0033.wav'])
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.
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 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.
Version | Tokenizer | Vocabulary Size | MCV7.0 dev | MCV7.0 test | MLS dev | MLS test | Voxpopuli dev | Voxpopuli test |
---|---|---|---|---|---|---|---|---|
1.5.0 | SentencePiece Unigram | 128 | 5.84 | 6.68 | 3.85 | 4.63 | 12.56 | 10.51 |
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.
References
- Downloads last month
- 283
Evaluation results
- Test WER on Common Voice 7test set self-reported6.680
- Test WER on Multilingual LibriSpeechtest set self-reported4.630
- Test WER on VoxPopuliself-reported10.510