Automatic Speech Recognition
NeMo
Safetensors
PyTorch
canary
automatic-speech-translation
speech
audio
Transformer
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Transformers
Eval Results (legacy)
Instructions to use CollectionStudio/canary-1b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use CollectionStudio/canary-1b-v2 with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("CollectionStudio/canary-1b-v2") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from CollectionStudio/canary-1b-v2: direct link, hf CLI and curl.
- Browser
- Download file 328 Bytes
-
https://huggingface.co/CollectionStudio/canary-1b-v2/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://CollectionStudio/canary-1b-v2/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/CollectionStudio/canary-1b-v2/resolve/main/tokenizer_config.json
328 Bytes
| { | |
| "backend": "tokenizers", | |
| "bos_token": "<|startoftranscript|>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|endoftext|>", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<pad>", | |
| "processor_class": "CanaryProcessor", | |
| "tokenizer_class": "TokenizersBackend", | |
| "unk_token": "<unk>" | |
| } | |