Automatic Speech Recognition
NeMo
Safetensors
PyTorch
English
speech
audio
Transformer
FastConformer
Conformer
NeMo
Qwen
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use nvidia/canary-qwen-2.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/canary-qwen-2.5b with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/canary-qwen-2.5b") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Comparison?
1
#18 opened 5 months ago
by
yukiarimo
Is streaming ASR possible?
#16 opened 7 months ago
by
ivoras
Run canary-qwen-2.5b on Jetson
🔥 2
#15 opened 7 months ago
by
raymondlo84
Updating the CUDA instruction
#14 opened 7 months ago
by
raymondlo84
Training and fine-tuning example
➕👍 3
7
#13 opened 8 months ago
by
shimohan
How does this stack up against Whisper ctranslate2?
1
#12 opened 8 months ago
by
1TBGPU4EVR
What is the basic formula to get this to run?
2
#11 opened 9 months ago
by
ASmith171
base model encoder choice
1
#8 opened 10 months ago
by
sugintama
用此模型训练希腊语的asr
1
#7 opened 10 months ago
by
smile9527
Chunked inference?
3
#6 opened 10 months ago
by
ponceoscarj
Does this model support diarization?
3
#5 opened 10 months ago
by
Cypherfox
How to get timestamps
1
#4 opened 10 months ago
by
Reggie
NeMo container for canary-qwen-2.5b
1
#3 opened 10 months ago
by
xinyuenn
Multi Lingual Version
🚀 3
2
#2 opened 10 months ago
by
Buttermilk03
支持其他语言的识别
1
#1 opened 10 months ago
by
wangweifei