NVIDIA Conformer-Transducer Large (fr) (FORK)
This model was trained on a composite dataset comprising of over 1500 hours of French speech. It is a large size version of Conformer-Transducer (around 120M parameters). See the model architecture section and NeMo documentation for complete architecture details.
NVIDIA NeMo: Training
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']
How to Use this Model
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.
Automatically instantiate the model
import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained("nvidia/stt_fr_conformer_transducer_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_fr_conformer_transducer_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-Transducer model is an autoregressive variant of Conformer model [1] for Automatic Speech Recognition which uses Transducer loss/decoding instead of CTC Loss. You may find more info on the detail of this model here: Conformer-Transducer 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 sentence-piece tokenizers [2] 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 over a thousand hours of French speech:
- MozillaCommonVoice 7.0 - 356 hours
- Multilingual LibriSpeech - 1036 hours
- VoxPopuli - 182 hours
Both models use same dataset, excluding a preprocessing step to strip hyphen from data for secondary model's training.
Performance
The performance of Automatic Speech Recognition models is measuring 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 latest model obtains the following greedy scores on the following evaluation datasets
- 6.85 % on MCV7.0 dev
- 7.95 % on MCV7.0 test
- 5.05 % on MLS dev
- 4.10 % on MLS test
Note that these evaluation datasets have been filtered and preprocessed to only contain French alphabet characters and are removed of punctuation outside of hyphenation and apostrophe.
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.
Further, since portions of the training set contain text from both pre- and post- 1990 orthographic reform, regularity of punctuation may vary between the two styles. For downstream tasks requiring more consistency, finetuning or downstream processing may be required. If exact orthography is not necessary, then using secondary model is advised.
References
- Downloads last month
- 1
Datasets used to train mexa-team/stt_fr_conformer_transducer_large
Evaluation results
- Dev WER on MCV 7.0self-reported6.850
- Test WER on MCV 7.0test set self-reported7.950
- Dev WER on Multilingual Librispeechself-reported5.050
- Test WER on Multilingual Librispeechtest set self-reported4.100