Squeezeformer Small model which has been trained on the Librispeech 960 hours corpus.
It utilizes a Google SentencePiece  tokenizer with vocabulary size 128, and transcribes text in lower case english alphabet along with spaces, apostrophes and a few other characters.
Squeezeformer CTC  model is an non-autoregressive, connectionist-temporal-classification based Automatic Speech Recognition model. You may find more info on the detail of this model here: Squeezeformer Model.
The tokenizers for these models were built using the text transcripts of the train set with this script.
All the models in this collection are trained on a composite dataset (NeMo ASRSET) comprising of several thousand hours of English speech:
- LibriSpeech 960 hours of English speech
The tokenizer for this model was built using text corpus provided with the train dataset.
We build a Google Sentencepiece Tokenizer  with the following script :
python [NEMO_GIT_FOLDER]/scripts/tokenizers/process_asr_text_tokenizer.py \
--data_root="<OUTPUT DIRECTORY FOR TOKENIZER>" \
The performance of Automatic Speech Recognition models is measuring using Word Error Rate.
The model obtains the following scores on the following evaluation datasets -
|Librispeech 960 h
Note that these scores on Librispeech are not particularly indicative of the quality of transcriptions that models trained on ASR Set will achieve, but they are a useful proxy.
How to Use this Model
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.
Automatically load the model from NGC
import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecCTCModelBPE.from_pretrained(model_name="stt_en_squeezeformer_ctc_small_ls")
Transcribing text with this model
python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py \
audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
This model accepts 16000 KHz 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.