Automatic Speech Recognition
NeMo
ONNX
GGUF
Danish
speech-recognition
speech-to-text
danish
danish-asr
offline
local-inference
cpu-inference
sherpa-onnx
rnnt
word-timestamps
Eval Results (legacy)
Instructions to use RyeAI/ekko-v1-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use RyeAI/ekko-v1-tiny with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("RyeAI/ekko-v1-tiny") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Commit History
2 days ago
-
Align comparison caption
Verified signature3658535 -
Refresh benchmark figures
Verified signaturecf8431b -
Align Ekko Tiny benchmark scores
Verified signature88b2df2
8 days ago
-
Name Ekko's NVIDIA base licence
Verified signature48cb3df
11 days ago
-
Date comparison to current leaderboard results
Verified signature950d88b -
Refresh comparison chart date to 9 October 2026
Verified signature2ac169d -
Tighten benchmark and export sections
Verified signaturee8b9148 -
Remove unavailable Common Voice dataset link
Verified signatured3344c6 -
Correct Common Voice benchmark naming
Verified signature09a7edf
15 days ago
-
Enlarge Tiny benchmark chart and show HF author avatars
Verified signature27ff726 -
Add under-800M Danish ASR benchmark comparison
Verified signature4834705
18 days ago
-
Link the Ekko STT runtime quickstart
Verified signaturedf068c7
23 days ago
-
Describe clear-speech and dictation use
Verified signaturee85f4a9 -
Document browser runtime configuration
Verified signatured9e7f6e -
Add browser ONNX runtime configuration
Verified signaturee37e698 -
Point Tiny card to updated license revision
Verified signature7e1c970 -
Clarify Ekko Tiny FT Speech notice
Verified signaturef107071
24 days ago
-
Point card to clean Tiny snapshot
Verified signature462575f -
Clean release snapshot
d89411a