Automatic Speech Recognition
Transformers
Safetensors
whisper
speech
audio
asr
multi-lingual
heep
heep-universal
entropy-based-curation
Instructions to use bc7ec356/heep-universal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bc7ec356/heep-universal with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="bc7ec356/heep-universal")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("bc7ec356/heep-universal") model = AutoModelForSpeechSeq2Seq.from_pretrained("bc7ec356/heep-universal") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -223,12 +223,7 @@ pipeline_tag: automatic-speech-recognition
|
|
| 223 |
---
|
| 224 |
|
| 225 |
|
| 226 |
-
#
|
| 227 |
-
|
| 228 |
-
**Addressing Q1 (Gain Attribution), Q2 (Baselines), and Q3 (Base Model Dependency)**
|
| 229 |
-
|
| 230 |
-
We apologize for the supplementary post after the rebuttal period. These results were finalized shortly after the deadline, and we wanted to ensure complete experimental evidence was available rather than leave placeholders.
|
| 231 |
-
|
| 232 |
|
| 233 |
### 🔗 Resources
|
| 234 |
|
|
@@ -276,8 +271,6 @@ To directly address concerns about generalization beyond Whisper V3 Turbo, we tr
|
|
| 276 |
|
| 277 |
4. **Reproducibility.** Model weights, curation code, and training scripts for both backbones are at the anonymous repository.
|
| 278 |
|
| 279 |
-
*We hope Reviewers 2ezj, oXjG, and S4Jd also find this supplementary evidence relevant to their earlier questions on generalization and controlled multilingual evaluation.*
|
| 280 |
-
|
| 281 |
---
|
| 282 |
|
| 283 |
## Model Overview
|
|
|
|
| 223 |
---
|
| 224 |
|
| 225 |
|
| 226 |
+
# Cross-Architecture Validation with HEEP-Indic
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 227 |
|
| 228 |
### 🔗 Resources
|
| 229 |
|
|
|
|
| 271 |
|
| 272 |
4. **Reproducibility.** Model weights, curation code, and training scripts for both backbones are at the anonymous repository.
|
| 273 |
|
|
|
|
|
|
|
| 274 |
---
|
| 275 |
|
| 276 |
## Model Overview
|