Automatic Speech Recognition
Transformers
Safetensors
English
moss
text-generation
speech
english
qwen3
audio
reinforcement-learning
custom_code
Eval Results (legacy)
Eval Results
Instructions to use OpenMOSS-Team/MOSS-Transcribe-preview-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMOSS-Team/MOSS-Transcribe-preview-2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="OpenMOSS-Team/MOSS-Transcribe-preview-2B", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("OpenMOSS-Team/MOSS-Transcribe-preview-2B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signaturec98175c -
Replace TTS-copied README with ASR-correct version (fix wrong-project badges, update model-index dataset id, drop placeholder image)
Verified signaturefc97aee -
Upload model weights (RL iter_9, sha256 3c453ea9...)
Verified signaturec4b3988 -
Initial release: MOSS-Transcribe-preview-2B (rebranded from internal Musci-ASR-2.4B v2 = RL iter_9 giga80-kl01)
Verified signature0124c6f -
initial commit
Verified signature6ff6439