Model Overview

This collection contains large size versions of Conformer-CTC (around 120M parameters) trained on NeMo ASRSet with over 1500 hours of French speech. Includes two models wtih separate tokenization sets, along with accompanying language models (n=4).

Utilizes a Google SentencePiece [1] tokenizer with vocabulary size 128, and transcribes text in lower case French alphabet along with spaces, apostrophes, and hyphens. Secondary model and associated language model (indicated with "no_hyphen" infix) omits hyphen from tokenization

Model Architecture

Conformer-CTC model is a non-autoregressive variant of Conformer model [2] 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 over a thousand hours of French speech:

• MozillaCommonVoice7.0 356 hours
• MultilingualLibreSpeech 1036 hours
• VoxPopuli 182 hours

Both models use same dataset, excluding a preprocessing step to strip hyphen from data for secondary model's training.

(Note: The MultiliingualLibreSpeech set includes orthography of both pre- and post- 1990 reform, which may affect predictability of hyphenation.)

Tokenizer Construction

The tokenizer for this model was built using text corpus provided with the train dataset.

We build a token set with the following script:

python [NEMO_GIT_FOLDER]/scripts/tokenizers/process_asr_text_tokenizer.py \
 --manifest="train_manifest.json" \
 --data_root="" \
 --vocab_size=128 \
 --tokenizer="spe" \
 --spe_type="unigram" \
 --spe_character_coverage=1.0 \
 --no_lower_case \
 --log

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

• 8.35 % on MCV7.0 dev
• 9.63 % on MCV7.0 test
• 5.88 % on MLS dev
• 4.91 % on MLS test

With 128 beam search and 4gram KenLM model (included with this model):

• 7.95 % on MCV7.0 dev
• 9.16 % on MCV7.0 test
• 5.57 % on MLS dev
• 4.66 % 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. For the secondary model trained without hyphenation, scores are slightly improved (see version sheet).

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 load the model from NGC

import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecCTCModelBPE.from_pretrained(model_name="stt_fr_conformer_ctc_large")

Transcribing text with this model

python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py \
 pretrained_name="stt_fr_conformer_ctc_large" \
 audio_dir=""

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.

Limitations

Since this model was trained on publically 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

[1] Conformer: Convolution-augmented Transformer for Speech Recognition

[2] Google Sentencepiece Tokenizer

[3] NVIDIA NeMo Toolkit

Licence

License to use this model is covered by the NGC TERMS OF USE unless another License/Terms Of Use/EULA is clearly specified. By downloading the public and release version of the model, you accept the terms and conditions of the NGC TERMS OF USE.