ContexNet-1024 model which was fine-tuned from English language to Spanish. We took a model trained on over 42,000 hours of English speech. Then we changed the model's decoder to output characters from the Spanish alphabet and fine-tuned this model using Spanish portions of the Mozilla CommonVoice (MCV7.0) , Multilingual LibriSpeech (MLS) , and Voxpopuli  training sets, as well as a subset of the Spanish Fisher dataset [5, 6]. This amounted to 1,340 hours of Spanish training data.
It utilizes a Google SentencePiece  tokenizer with vocabulary size 1024, and transcribes text in lower case Spanish alphabet characters.
ContextNet  model is an autoregressive, transducer based Automatic Speech Recognition model. You may find more info on the detail of this model here: ContextNet Model.
The NeMo toolkit  was used for training this model over several hundred epochs on multiple GPUs.
While finetuning this model, we used the following datasets:
The tokenizer for this model was built using the text that was in the training set.
We build a Google Sentencepiece Tokenizer with the following script:
python [NEMO_GIT_FOLDER]/scripts/process_asr_text_tokenizer.py \ --manifest="train_manifest.json" \ --data_root="<OUTPUT DIRECTORY FOR TOKENIZER>" \ --vocab_size=1024 \ --tokenizer="spe" \ --spe_type="unigram" \ --spe_character_coverage=1.0 \ --no_lower_case \ --log
The performance of Automatic Speech Recognition models is measuring using Word Error Rate.
The model obtains the following greedy scores on the following evaluation datasets:
The model is available for use in the NeMo toolkit , and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.EncDecCTCModelBPE.from_pretrained(model_name="stt_es_contextnet_1024")
python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py \ pretrained_name="stt_es_contextnet_1024" \ audio_dir=""
This model accepts 16000 Hz Mono-channel Audio (wav files) as input.
This model provides transcribed speech as a string for a given audio sample.
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.