Automatic Speech Recognition
Transformers
Safetensors
Chinese
English
ming_v3_asr
text-generation
audio
speech-recognition
contextual-asr
custom_code
Instructions to use ml-resources/Ming-3.0-asr-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ml-resources/Ming-3.0-asr-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ml-resources/Ming-3.0-asr-tiny", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("ml-resources/Ming-3.0-asr-tiny", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from ml-resources/Ming-3.0-asr-tiny: direct link, hf CLI and curl.
- Browser
- Download file 670 Bytes
-
https://huggingface.co/ml-resources/Ming-3.0-asr-tiny/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://ml-resources/Ming-3.0-asr-tiny/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/ml-resources/Ming-3.0-asr-tiny/resolve/main/preprocessor_config.json
670 Bytes
| { | |
| "feature_extractor_type": "MingV3ASRFeatureExtractor", | |
| "processor_class": "MingV3ASRProcessor", | |
| "feature_size": 128, | |
| "sampling_rate": 16000, | |
| "padding_value": 0.0, | |
| "audio_config": { | |
| "n_mels": 128, | |
| "n_audio_ctx": 3000, | |
| "n_audio_state": 1280, | |
| "n_audio_head": 20, | |
| "n_audio_layer": 32, | |
| "downsampler_kernel_size_list": [ | |
| 3 | |
| ], | |
| "downsampler_stride_list": [ | |
| 2 | |
| ], | |
| "chunk_frames": 3000, | |
| "downsampler_padding_list": [ | |
| 1 | |
| ] | |
| }, | |
| "auto_map": { | |
| "AutoFeatureExtractor": "feature_extraction_ming_v3_asr.MingV3ASRFeatureExtractor", | |
| "AutoProcessor": "processing_ming_v3_asr.MingV3ASRProcessor" | |
| } | |
| } | |