de-coder/stt_sw_ctc_model

1---2language:3- rw4license: cc-by-4.05library_name: nemo6datasets:7- mozilla-foundation/common_voice_11_08thumbnail: null9tags:10- automatic-speech-recognition11- speech12- Kinyarwanda13- audio14- CTC15- Conformer16- Transformer17- NeMo18- pytorch19model-index:20- name: stt_rw_conformer_ctc_large21  results: []22 23---24 25 26## Model Overview27 28<DESCRIBE IN ONE LINE THE MODEL AND ITS USE>29 30## NVIDIA NeMo: Training31 32To train, fine-tune or play with the model you will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo). We recommend you install it after you've installed latest Pytorch version.33```34pip install nemo_toolkit['all']35``` 36 37## How to Use this Model38 39The 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.40 41### Automatically instantiate the model42 43```python44import nemo.collections.asr as nemo_asr45asr_model = nemo_asr.models.ASRModel.from_pretrained("yonas/stt_rw_conformer_ctc_large")46```47 48### Transcribing using Python49First, let's get a sample50```51wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav52```53Then simply do:54```55asr_model.transcribe(['2086-149220-0033.wav'])56```57 58### Transcribing many audio files59 60```shell61python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py  pretrained_name="yonas/stt_rw_conformer_ctc_large"  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"62```63 64### Input65 66This model accepts 16000 KHz Mono-channel Audio (wav files) as input.67 68### Output69 70This model provides transcribed speech as a string for a given audio sample.71 72## Model Architecture73 74<ADD SOME INFORMATION ABOUT THE ARCHITECTURE>75 76## Training77 78<ADD INFORMATION ABOUT HOW THE MODEL WAS TRAINED - HOW MANY EPOCHS, AMOUNT OF COMPUTE ETC>79 80### Datasets81 82<LIST THE NAME AND SPLITS OF DATASETS USED TO TRAIN THIS MODEL (ALONG WITH LANGUAGE AND ANY ADDITIONAL INFORMATION)>83 84## Performance85 86<LIST THE SCORES OF THE MODEL - 87      OR88USE THE Hugging Face Evaluate LiBRARY TO UPLOAD METRICS>89 90## Limitations91 92<DECLARE ANY POTENTIAL LIMITATIONS OF THE MODEL>93 94Eg: 95Since 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.96 97 98## References99 100<ADD ANY REFERENCES HERE AS NEEDED>101 102[1] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo)103 104