Instructions to use Reson8/Rumble-2-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Reson8/Rumble-2-Flash with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Reson8/Rumble-2-Flash")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Reson8/Rumble-2-Flash") model = AutoModelForMultimodalLM.from_pretrained("Reson8/Rumble-2-Flash", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
3 days ago
-
German average: match leaderboard rounding
Verified signaturea7d2472 -
Multilingual track: single table, no RTFx
Verified signature9eb1ffd -
Multilingual track: one table per language with average
Verified signature2ff67e0 -
Match leaderboard aggregates for the private rows; no RTFx for them
Verified signaturee2e3182 -
Add private scripted/conversational splits to English track
Verified signatured2be248 -
Add Open ASR Leaderboard results (English and multilingual)
Verified signatureResults from the Open ASR Leaderboard, English and multilingual tracks, with RTFx.2bb067e -
Simplify Transformers usage snippet (#2)
- Simplify Transformers usage snippet (0b4f80b77cacc42041808b6c0ca412cec4cac0d1) - Use AutoModelForMultimodalLM (f15413b3bee1dd390a7d18a6017964cf3c9f8bed) - Use hf.co short URL for the sample audio (62c9ce36bf96e4d49c60176889fb1bc0689b7395) - Rely on the checkpoint dtype (bfloat16) by default (b436e35bbb1cf066541c88501977c68df2a01eb6) - Move language auto-detection note into a code comment (7d056179e79825d34315bc28a55d4df558dd4c28) - Move return_format note into a code comment (74dc78acacacef965d24dfee365849cab065a6a7) - Clarify return_format comment (74cef837fe6d2f3d79a9082b6888732846060f5e) - Shorten return_format comment (1f683bef7118fff9f8941bc62c1ecef2cb3c4686) - Inline return_format comment (23844ce1a5ab8e75894ad5ce8c8748879e01c528) Co-authored-by: Eustache Le Bihan <eustlb@users.noreply.huggingface.co>a21c97c
5 days ago
-
Update model card/licensing and simplify CTC helper.
5d7cb99
11 days ago
-
Update Rumble-2-Flash weights (2026-11-10) + auxiliary CTC head
Verified signatureNew weights converted with the same native-Transformers key mapping as the previous upload; config, tokenizer, chat template and processor files unchanged. Adds ctc_head.py and ctc/ (auxiliary CTC head + vocab) and a README section.ec9a91b
24 days ago
-
Update README to use Rumble-2-Flash name
Verified signaturee2e60d8
25 days ago
-
Update README for Serval-2-Flash rename
Verified signatureUpdate the model title and all usage examples to Reson8/Serval-2-Flash.92e36f7
29 days ago
-
Simplify README to installation, inference and transcription options
Verified signature39cbf90 -
Convert Resonant-Light to native Transformers format
Verified signatureConvert with the official HF Qwen3-ASR script; preserve custom token IDs, tied embeddings, and Reson8 chat controls. All 457 stored tensors match exactly; native reload and CPU transcription validated. Preserve all existing README text and append native Transformers usage.3a9a06e
-
Update model weights
Reson8Verified signature696b58d
-
README: transformers (qwen-asr) example
Reson8Verified signature0700281 -
Resonant-Light
Reson8Verified signature1f197da -
initial commit
Reson8Verified signature4907355