Automatic Speech Recognition
Transformers
Safetensors
zero_swot_encoder
feature-extraction
zeroswot
speech translation
zero-shot
end-to-end
nllb
wav2vec2
custom_code
Instructions to use johntsi/ZeroSwot-Medium_asr-mustc_en-to-200 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use johntsi/ZeroSwot-Medium_asr-mustc_en-to-200 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="johntsi/ZeroSwot-Medium_asr-mustc_en-to-200", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("johntsi/ZeroSwot-Medium_asr-mustc_en-to-200", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "johntsi/ZeroSwot-Medium_asr-mustc_en-to-200/model.safetensors", | |
| "architectures": [ | |
| "ZeroSwotEncoderModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "model.ZeroSwotEncoderConfig", | |
| "AutoModel": "model.ZeroSwotEncoderModel" | |
| }, | |
| "compression_adapter": { | |
| "blank_idx": 0, | |
| "dropout": 0.1, | |
| "embed_dim": 1024, | |
| "sep_idx": 4, | |
| "transformer_layers": 3 | |
| }, | |
| "embed_dim": 1024, | |
| "model_type": "zero_swot_encoder", | |
| "nllb_model_name_or_path": "facebook/nllb-200-distilled-600M", | |
| "speech_embedder": { | |
| "nllb_eng_id": 256047, | |
| "nllb_eos_id": 2 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.2", | |
| "wav2vec2_model_name_or_path": "facebook/wav2vec2-large-960h-lv60-self" | |
| } | |