Multilingual ASR for Kinyarwanda, Swahili, and Luganda
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.ASRModel.from_pretrained("mbazaNLP/stt_rw_sw_lg_conformer_ctc_large")
First, let's get a sample
Then simply do:
python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py pretrained_name="mbazaNLP/stt_rw_sw_lg_conformer_ctc_large" 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.
<ADD INFORMATION ABOUT HOW THE MODEL WAS TRAINED - HOW MANY EPOCHS, AMOUNT OF COMPUTE ETC>
<LIST THE NAME AND SPLITS OF DATASETS USED TO TRAIN THIS MODEL (ALONG WITH LANGUAGE AND ANY ADDITIONAL INFORMATION)>
<LIST THE SCORES OF THE MODEL - OR USE THE Hugging Face Evaluate LiBRARY TO UPLOAD METRICS>
Eg: 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.
- Downloads last month