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
Match leaderboard aggregates for the private rows; no RTFx for them
Browse files
README.md
CHANGED
|
@@ -137,7 +137,7 @@ Evaluated on the [Open ASR Leaderboard](https://huggingface.co/spaces/hf-audio/o
|
|
| 137 |
|
| 138 |
### English track
|
| 139 |
|
| 140 |
-
Average WER
|
| 141 |
|
| 142 |
| Split | WER (%) | RTFx |
|
| 143 |
|---|---|---|
|
|
@@ -148,8 +148,8 @@ Average WER over the 7 default public splits: **6.08** (RTFx 6338). The two priv
|
|
| 148 |
| URGENT24 | 10.25 | 3314 |
|
| 149 |
| Voice Arena Monsoon | 3.56 | 3760 |
|
| 150 |
| VoxPopuli | 2.43 | 4222 |
|
| 151 |
-
| Private (scripted) |
|
| 152 |
-
| Private (conversational) | 13.
|
| 153 |
|
| 154 |
### Multilingual track
|
| 155 |
|
|
|
|
| 137 |
|
| 138 |
### English track
|
| 139 |
|
| 140 |
+
Average WER on the leaderboard: **6.60** (RTFx 6338), over the 7 public splits plus the aggregated Private (scripted) and Private (conversational) scores.
|
| 141 |
|
| 142 |
| Split | WER (%) | RTFx |
|
| 143 |
|---|---|---|
|
|
|
|
| 148 |
| URGENT24 | 10.25 | 3314 |
|
| 149 |
| Voice Arena Monsoon | 3.56 | 3760 |
|
| 150 |
| VoxPopuli | 2.43 | 4222 |
|
| 151 |
+
| Private (scripted) | 3.71 | |
|
| 152 |
+
| Private (conversational) | 13.14 | |
|
| 153 |
|
| 154 |
### Multilingual track
|
| 155 |
|