GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Sunbird
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Sunbird
Model Tree
jq/whisper-large-v3-salt-plus-xog-myx-kin-swa
Input Modalities
Output Modalities
Supported Functionality
The model was trained with the SALT dataset, Common Voice (Luganda, Swahili, Kinyarwanda), Google FLEURS and Makerere Yogera datasets. To help with generalisation in practical settings, training used addition of random noise and random downsampling to 8kHz to simulate phone speech. Street noise sampled from urban locations in Uganda was added to improve robustness.
The model is used in a similar way to the base Whisper model. The model will attempt to auto-detect the language and provide a transcription. However, note that language detection is not always accurate and results may be improved by specifying it instead. The languages in this model are not supported by the base Whisper model, so the format is slightly different:
python
import transformersimport datasetsimport torch processor = transformers.WhisperProcessor.from_pretrained( "Sunbird/asr-whisper-large-v3-salt")model = transformers.WhisperForConditionalGeneration.from_pretrained( "Sunbird/asr-whisper-large-v3-salt") SALT_LANGUAGE_TOKENS_WHISPER = { 'eng': 50259, # English (Ugandan) 'swa': 50318, # Swahili 'ach': 50357, # Acholi 'lgg': 50356, # Lugbara 'lug': 50355, # Luganda 'nyn': 50354, # Runyankole 'teo': 50353, # Ateso 'xog': 50352, # Lusoga 'ttj': 50351, # Rutooro 'kin': 50350, # Kinyarwanda 'myx': 50349, # Lumasaba} # Get some test audiods = datasets.load_dataset('Sunbird/salt', 'multispeaker-lug', split='test')audio = ds[0]['audio']sample_rate = ds[0]['sample_rate'] # Specify a language from one of the above.lang = 'lug' # Apply the modeldevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")input_features = processor( audio, sampling_rate=sample_rate, return_tensors="pt").input_featuresinput_features = input_features.to(device)predicted_ids = model.to(device).generate( input_features, # Optionally set language=None here instead to auto-detect. language=processor.tokenizer.decode(SALT_LANGUAGE_TOKENS_WHISPER[lang]), forced_decoder_ids=None)transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True) print(transcription)# Ekikoola kya kasooli kya kyenvu wabula langi yaakyo etera okuba eya kitaka wansi.Evaluated on SALT text and held-out split from Common Voice (swa, kin) and Yogera (ttj, xog).
bibtex
@misc{sunbird2025whisperlargev3, title = {asr-whisper-large-v3-salt}, author = {{Sunbird AI}}, year = {2025}, howpublished = {\url{https://huggingface.co/Sunbird/asr-whisper-large-v3-salt}}, note = {Whisper large for Ugandan languages}}import transformersimport datasetsimport torch processor = transformers.WhisperProcessor.from_pretrained( "Sunbird/asr-whisper-large-v3-salt")model = transformers.WhisperForConditionalGeneration.from_pretrained( "Sunbird/asr-whisper-large-v3-salt") SALT_LANGUAGE_TOKENS_WHISPER = { 'eng': 50259, # English (Ugandan) 'swa': 50318, # Swahili 'ach': 50357, # Acholi 'lgg': 50356, # Lugbara 'lug': 50355, # Luganda 'nyn': 50354, # Runyankole 'teo': 50353, # Ateso 'xog': 50352, # Lusoga 'ttj': 50351, # Rutooro 'kin': 50350, # Kinyarwanda 'myx': 50349, # Lumasaba} # Get some test audiods = datasets.load_dataset('Sunbird/salt', 'multispeaker-lug', split='test')audio = ds[0]['audio']sample_rate = ds[0]['sample_rate'] # Specify a language from one of the above.lang = 'lug' # Apply the modeldevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")input_features = processor( audio, sampling_rate=sample_rate, return_tensors="pt").input_featuresinput_features = input_features.to(device)predicted_ids = model.to(device).generate( input_features, # Optionally set language=None here instead to auto-detect. language=processor.tokenizer.decode(SALT_LANGUAGE_TOKENS_WHISPER[lang]), forced_decoder_ids=None)transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True) print(transcription)# Ekikoola kya kasooli kya kyenvu wabula langi yaakyo etera okuba eya kitaka wansi.@misc{sunbird2025whisperlargev3, title = {asr-whisper-large-v3-salt}, author = {{Sunbird AI}}, year = {2025}, howpublished = {\url{https://huggingface.co/Sunbird/asr-whisper-large-v3-salt}}, note = {Whisper large for Ugandan languages}}