Views
No views yet
| Audio | Human Transcription | ASR Transcription | |
|---|---|---|---|
| 1 | Katika soko kuna duka la matunda na mboga likiwa na bidhaa zilizopangwa vizuri. Vitu mbalimbali kama karoti, mahindi, nyanya na viazi vimepangwa kwenye meza. | katika soko kuna duka la matunda na mboga likiwa na bidhaa zilizopangwa vizuri vitu mbalimbali kama karoti mahindi nyanya na viazi vimepangwa kwenye meza | |
| 2 | Maji ni uhai.Mifereji ya kuwezesha wananchi kuchota maji ya kunywa na pia ya matumizi nyumbani.Ni vyema kuhifadhi maji kwa njia inayofaa. | maji ni uhai mifereji ya kuwezesha wananchi kuchota maji ya kunywa na pia ya matumizi nyumbani ni vyema kuhifadhi maji kwa njia inayofaa | |
| 3 | Barabara yenye shughuli nyingi ambapo watu wengi wanasubiri au wanapanda mabasi mawili ya abiria. Mabasi yote mawili yana muundo wa matatu yakionyesha sanaa na rangi mbali mbali na yametayarishwa kubeba abiria. | barabara yenye shughuli nyingi ambapo watu wengi wanasubiri au wanapanda mabasi mawili ya abiria mabasi yote mawili yana muundo wa matatu yakionyesha sanaa na rangi mbalimbali na yametayarishwa kubeba abiria |
1from transformers import Wav2Vec2BertProcessor, Wav2Vec2BertForCTC
2import torch
3import torchaudio
4
5# load model and processor
6processor = Wav2Vec2BertProcessor.from_pretrained("badrex/w2v-bert-2.0-swahili-asr")
7model = Wav2Vec2BertForCTC.from_pretrained("badrex/w2v-bert-2.0-swahili-asr")
8
9# load audio
10audio_input, sample_rate = torchaudio.load("path/to/audio.wav")
11
12# preprocess
13inputs = processor(audio_input.squeeze(), sampling_rate=sample_rate, return_tensors="pt")
14
15# inference
16with torch.no_grad():
17 logits = model(**inputs).logits
18
19# decode
20predicted_ids = torch.argmax(logits, dim=-1)
21transcription = processor.batch_decode(predicted_ids)[0]
22print(transcription)1@misc{w2v_bert_swahili_asr,
2 author = {Badr M. Abdullah},
3 title = {Adapting Wav2Vec2-BERT 2.0 for Swahili ASR},
4 year = {2025},
5 publisher = {Hugging Face},
6 url = {https://huggingface.co/badrex/w2v-bert-2.0-swahili-asr}
7}
8