cdli/ugandan_english_nonstandard_speech_v1.0
Viewer • Updated • 7.25k • 321 • 1
How to use KasuleTrevor/cdli-whisper-lg-sunbird-decoder-a40 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="KasuleTrevor/cdli-whisper-lg-sunbird-decoder-a40") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("KasuleTrevor/cdli-whisper-lg-sunbird-decoder-a40")
model = AutoModelForSpeechSeq2Seq.from_pretrained("KasuleTrevor/cdli-whisper-lg-sunbird-decoder-a40", device_map="auto")This model is a fine-tuned version of Sunbird/asr-whisper-large-v3-salt on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.7206 | 1.3555 | 500 | 0.7973 | 0.5930 | 0.3265 |
| 0.7191 | 2.7110 | 1000 | 0.7640 | 0.5767 | 0.3136 |
| 0.6502 | 4.0651 | 1500 | 0.7631 | 0.5714 | 0.3097 |
| 0.637 | 5.4206 | 2000 | 0.7613 | 0.5656 | 0.3069 |