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 config.json from CollectionStudio/canary-1b-v2: direct link, hf CLI and curl.
- Browser
- Download file 1.59 kB
-
https://huggingface.co/CollectionStudio/canary-1b-v2/resolve/main/config.json
- Command line
-
hf download hf://CollectionStudio/canary-1b-v2/config.json
-
curl -L -o config.json https://huggingface.co/CollectionStudio/canary-1b-v2/resolve/main/config.json
1.59 kB
| { | |
| "architectures": [ | |
| "CanaryForConditionalGeneration" | |
| ], | |
| "bos_token_id": 4, | |
| "decoder_config": { | |
| "attention_bias": true, | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 4, | |
| "eos_token_id": 3, | |
| "head_dim": 128, | |
| "hidden_act": "relu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "max_position_embeddings": 1024, | |
| "model_type": "canary_decoder", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 8, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 2, | |
| "use_cache": true, | |
| "vocab_size": 16384 | |
| }, | |
| "decoder_start_token_id": 7, | |
| "dtype": "float32", | |
| "encoder_config": { | |
| "activation_dropout": 0.1, | |
| "attention_bias": true, | |
| "attention_dropout": 0.1, | |
| "conv_kernel_size": 9, | |
| "convolution_bias": true, | |
| "dropout": 0.1, | |
| "dropout_positions": 0.0, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layerdrop": 0.1, | |
| "max_position_embeddings": 5000, | |
| "model_type": "parakeet_encoder", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "num_mel_bins": 128, | |
| "scale_input": false, | |
| "subsampling_conv_channels": 256, | |
| "subsampling_conv_kernel_size": 3, | |
| "subsampling_conv_stride": 2, | |
| "subsampling_factor": 8 | |
| }, | |
| "eos_token_id": 3, | |
| "initializer_range": 0.02, | |
| "is_encoder_decoder": true, | |
| "model_type": "canary", | |
| "pad_token_id": 2, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.15.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 16384 | |
| } | |