language:
- uk
library_name: nemo
datasets:
- common_voice
tags:
- automatic-speech-recognition
- speech
- audio
- CTC
- Citrinet
- Transformer
- pytorch
- NeMo
- hf-asr-leaderboard
- Riva
license: cc-by-4.0
NVIDIA Streaming Citrinet 1024 (uk)
| 
This model transcribes speech in lowercase Ukrainian alphabet including spaces and apostrophes, and is trained on 69 hours of Ukrainian speech data. It is a non-autoregressive "large" variant of Streaming Citrinet, with around 141 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 the latest PyTorch version.
pip install nemo_toolkit['all']
Automatically instantiate the model
import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecCTCModel.from_pretrained("nvidia/stt_zh_citrinet_1024_gamma_0_25")
Transcribing using Python
First, let's get a sample of spoken Mandarin Chinese.
Then simply do:
asr_model.transcribe(['<Path of audio file(s)>'])
Transcribing many audio files
python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
pretrained_name="nvidia/stt_zh_citrinet_1024_gamma_0_25"
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
Streaming Citrinet-1024 model is a non-autoregressive, streaming variant of Citrinet model [1] for Automatic Speech Recognition which uses CTC loss/decoding instead of Transducer. You may find more info on this model here: Citrinet Model.
Training
The NeMo toolkit [3] was used for training the model for over several hundred epochs. This model was trained with this example script and this base config.
The tokenizer for this models was built using the text transcripts of the train set with this script.
Datasets
Model is trained on Mozilla Common Voice Corpus 10.0 dataset comprising of 69 hours of Ukrainian speech.
Limitations
Since this model was trained on publicly available speech datasets, the performance of this model might degrade for speech that 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
[1] Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition
[2] Google Sentencepiece Tokenizer
[3] NVIDIA NeMo Toolkit