Stt Be Fastconformer Hybrid Large Pc

🚀 NVIDIA FastConformer-Hybrid Large (be)

This model transcribes speech in upper and lower case Belarusian alphabet along with spaces, periods, commas, and question marks. It is a "large" version of FastConformer Transducer-CTC model with around 115M parameters and is trained on two losses: Transducer and CTC.

| | |

🚀 Quick Start

To start using this model, you first need to install NVIDIA NeMo. It is recommended to install it after installing the latest Pytorch version.

pip install nemo_toolkit['all']

✨ Features

• Transcribes speech in upper and lower case Belarusian alphabet, including spaces, periods, commas, and question marks.
• A "large" version of FastConformer Transducer - CTC model with around 115M parameters.
• A hybrid model trained on two losses: Transducer (default) and CTC.

📦 Installation

To train, fine - tune or play with the model, you need to install NVIDIA NeMo.

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.EncDecHybridRNNTCTCBPEModel.from_pretrained(model_name="nvidia/stt_be_fastconformer_hybrid_large_pc")

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

Using Transducer mode inference:

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

Using CTC mode inference:

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

📚 Documentation

Input

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

Output

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

Model Architecture

FastConformer [1] is an optimized version of the Conformer model with 8x depthwise - separable convolutional downsampling. The model is trained in a multitask setup with joint Transducer and CTC decoder loss. You may find more information on the details of FastConformer here: Fast - Conformer Model and about Hybrid Transducer - CTC training here: Hybrid Transducer - CTC.

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 MCV12 BY corpus comprising of 1500 hours of Belarusian speech.

Performance

The performance of Automatic Speech Recognition models is measured using Word Error Rate. Since this dataset is trained on multiple domains and a much larger corpus, it will generally perform better at transcribing audio in general.

The following tables summarize the performance of the available models in this collection with the Transducer decoder. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding.

a) On data without Punctuation and Capitalization with Transducer decoder

b) On data with Punctuation and Capitalization with Transducer decoder

Limitations

⚠️ Important Note

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. The model only outputs the punctuations: '.', ',', '?' and hence might not do well in scenarios where other punctuations are also expected.

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

FastConformer is an optimized version of the Conformer model with 8x depthwise - separable convolutional downsampling. It is trained in a multitask setup with joint Transducer and CTC decoder loss. For more details, refer to Fast - Conformer Model and Hybrid Transducer - CTC.

📄 License

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] Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition [2] Google Sentencepiece Tokenizer [3] NVIDIA NeMo Toolkit