Automatic Speech Recognition
Transformers
Safetensors
Danish
cohere_asr
audio
speech-recognition
transcription
danish
hf-asr-leaderboard
custom_code
Instructions to use syvai/hviske-v5.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use syvai/hviske-v5.3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="syvai/hviske-v5.3", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("syvai/hviske-v5.3", trust_remote_code=True) model = AutoModelForSpeechSeq2Seq.from_pretrained("syvai/hviske-v5.3", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload hviske-v5.3: LLRD mult=0.75, 5 epochs — full-test avg WER 15.56% (read_aloud 10.26%, conv 21.30%)
17aa942 verified Download preprocessor_config.json from syvai/hviske-v5.3: direct link, hf CLI and curl.
- Browser
- Download file 420 Bytes
-
https://huggingface.co/syvai/hviske-v5.3/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://syvai/hviske-v5.3/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/syvai/hviske-v5.3/resolve/main/preprocessor_config.json
420 Bytes
| { | |
| "auto_map": { | |
| "AutoFeatureExtractor": "processing_cohere_asr.CohereAsrFeatureExtractor" | |
| }, | |
| "dither": 1e-05, | |
| "feature_extractor_type": "CohereAsrFeatureExtractor", | |
| "feature_size": 128, | |
| "frame_splicing": 1, | |
| "log": true, | |
| "n_fft": 512, | |
| "n_window_size": 400, | |
| "n_window_stride": 160, | |
| "normalize": "per_feature", | |
| "pad_to": 0, | |
| "padding_value": 0.0, | |
| "sampling_rate": 16000, | |
| "window": "hann" | |
| } | |