Downloads · 30 days
2
7% of all-time downloads
yehoshua01/waxal-whisper-turbo-lin-r1
waxal-whisper-turbo-lin-r1 is a automatic speech recognition model from yehoshua01. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
Component of the 4th-place solution to the Google WAXAL ASR Challenge (Zindi, phase 2): 892 unseen clips, two African languages, no language metadata, scored 1 - (WER + CER) / 2 on raw text. Private leaderboard 0.7718…
Downloads · 30 days
2
7% of all-time downloads
All-time downloads
27
Public
Parameters
809M
3.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.2 GB · 100%
From the Hugging Face model README
Component of the 4th-place solution to the Google WAXAL ASR Challenge (Zindi, phase 2):
892 unseen clips, two African languages, no language metadata, scored 1 - (WER + CER) / 2 on
raw text. Private leaderboard 0.771848284.
Code, full method and one-command verification: yehoshua0/waxal-asr-phase2 The repository reproduces the submitted CSV byte for byte on a laptop in about a minute, and re-decodes every input from the audio on rented GPUs in about four hours.
Witness (voter), and the one the shipped chain actually reads. Decode it under the placeholder language token <|sw|>, which is what it trained under: a language token is a learned decoder state, and <|ln|> selects one this checkpoint never saw.
Beam 3 gains +0.003369 over greedy on this checkpoint. As a solo Lingala half it scores 0.752910, i.e. -0.009491 against the shipped chain.
from transformers import WhisperForConditionalGeneration, WhisperProcessor
import torch, soundfile as sf, torchaudio.functional as AF
proc = WhisperProcessor.from_pretrained("yehoshua01/waxal-whisper-turbo-lin-r1")
model = WhisperForConditionalGeneration.from_pretrained("yehoshua01/waxal-whisper-turbo-lin-r1").eval().cuda()
tok = proc.tokenizer
# the language slot is a LEARNED decoder state -- use the token this checkpoint trained under
forced = [(1, tok.convert_tokens_to_ids("<|sw|>")),
(2, tok.convert_tokens_to_ids("<|transcribe|>")),
(3, tok.convert_tokens_to_ids("<|notimestamps|>"))]
wav, sr = sf.read("clip.wav", dtype="float32")
wav = AF.resample(torch.from_numpy(wav), sr, 16_000).numpy()[:30 * 16_000]
f = proc.feature_extractor(wav, sampling_rate=16_000, return_tensors="pt").input_features
out = model.generate(f.to("cuda", model.dtype), forced_decoder_ids=forced, max_new_tokens=220)
print(proc.batch_decode(out, skip_special_tokens=True)[0])
| code, method, verification | yehoshua0/waxal-asr-phase2 |
| cached decodes and chain inputs | yehoshua01/waxal-phase2-chain-inputs |
| all checkpoints | yehoshua01 on the Hub |
Sibling checkpoints (primaries, voters and ablations of the same system): waxal-mms-1b-lin-pl2-spk · waxal-sunbird51-sna-pl2-spk · waxal-whisper-turbo-lin-r2 · waxal-qlora-largev3-lin · waxal-omni-ctc1b-lin · waxal-omni-ctc1b-sna · waxal-sunbird51-lin-ft-r2 · waxal-sunbird51-lin-ft-light · waxal-mms-1b-lin-full · waxal-mms-1b-lin-fullmeta · waxal-ssa-hubert-lin
apache-2.0. Training data is google/WaxalNLP
(CC-BY-SA-4.0, share-alike), so derivatives carry that too.
These weights are not a general-purpose ASR model. Pseudo-labels were computed on the phase-2 test audio (transductive self-training, permitted for phase-2 training by the host), so the checkpoint is partly adapted to that specific set.