Automatic Speech Recognition
Transformers
Safetensors
English
musci
text-generation
speech-to-text
asr
speech
english
qwen3
audio
reinforcement-learning
custom_code
Eval Results (legacy)
Eval Results
Instructions to use Musci-research/Musci-ASR-2.4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Musci-research/Musci-ASR-2.4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Musci-research/Musci-ASR-2.4B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Musci-research/Musci-ASR-2.4B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,8 +16,6 @@ Qwen3-Omni-MoE audio encoder. Trained on public English ASR corpora and tuned wi
|
|
| 16 |
reinforcement learning on the Open ASR Leaderboard training splits. Total \~2.4B parameters,
|
| 17 |
distributed as a single `bfloat16` safetensors shard (\~4.84 GB).
|
| 18 |
|
| 19 |
-
Submitted to the
|
| 20 |
-
[Open ASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard).
|
| 21 |
|
| 22 |
## Inference
|
| 23 |
|
|
|
|
| 16 |
reinforcement learning on the Open ASR Leaderboard training splits. Total \~2.4B parameters,
|
| 17 |
distributed as a single `bfloat16` safetensors shard (\~4.84 GB).
|
| 18 |
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Inference
|
| 21 |
|