Automatic Speech Recognition
Transformers
PyTorch
JAX
TensorBoard
Safetensors
Norwegian
whisper
audio
asr
hf-asr-leaderboard
Instructions to use NbAiLabArchive/scream_medium_beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLabArchive/scream_medium_beta with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NbAiLabArchive/scream_medium_beta")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("NbAiLabArchive/scream_medium_beta") model = AutoModelForSpeechSeq2Seq.from_pretrained("NbAiLabArchive/scream_medium_beta", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "add_bos_token": false, | |
| "add_prefix_space": true, | |
| "bos_token": { | |
| "__type": "AddedToken", | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "clean_up_tokenization_spaces": true, | |
| "dropout": 0.1, | |
| "eos_token": { | |
| "__type": "AddedToken", | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "errors": "replace", | |
| "model_max_length": 1024, | |
| "pad_token": null, | |
| "processor_class": "WhisperProcessor", | |
| "return_attention_mask": false, | |
| "tokenizer_class": "WhisperTokenizer", | |
| "unk_token": { | |
| "__type": "AddedToken", | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |