Instructions to use mispeech/dasheng-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mispeech/dasheng-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="mispeech/dasheng-base", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mispeech/dasheng-base", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
12 days ago
-
Fix batched inputs longer than target_length (clips mixed) and keep the last full segment
Verified signatureFor inputs longer than `target_length` (1008 frames in the released configs, ~10.1 s), `AudioTransformerMAE_Encoder.forward` splits the spectrogram into segments and encodes all of them as one batch. This PR fixes two problems in that path. **1. Clips in a batch get mixed.** `torch.flatten(splits, 0, 1)` orders the first axis as (segment, batch), but `torch.reshape(x, (x.shape[0] // n_splits, -1, C))` reads it back as (batch, segment). With batch size > 1, each output row contains segments of other clips. Batch size 1 is not affected, which is why single-clip checks look fine. The fix reshapes as (segment, batch, time, C), swaps the first two axes and joins segments along time. The pip `dasheng` package encodes each segment separately and concatenates along time, so it already behaves this way. **2. The last segment is dropped when the length is an exact multiple of `target_length`.** The `else` branch stacks `splits[:-1]` even though the last split is full, so e.g. 2 x 1008 input fr…8fbd233
-
Fix `Tensor.item() cannot be called on meta tensors` error during loading with transformers>=5 (#1)
- Fix `Tensor.item() cannot be called on meta tensors` error during loading with transformers>=5 (b694d074577fdd74ddd12c77f459a8e2774eb351) Co-authored-by: zhoukz <zhoukz@users.noreply.huggingface.co>d29a721
-
Update feature_extraction_dasheng.py
Verified signaturece45305
-
Update README.md
Verified signaturebd8db95 -
Update README.md
Verified signatured8f28a2 -
Update config.json
Verified signature5835415 -
Update config.json
Verified signaturec314ac7 -
Update config.json
Verified signature56e3833 -
Update README.md
Verified signatureb73b6c9 -
Update README.md
Verified signaturee845783 -
Update config.json
Verified signaturedbe0e17 -
Update preprocessor_config.json
Verified signaturec91f168 -
Upload 3 files
Verified signature3a4d7b4
-
Update README.md
Verified signature24ac28c
-
Update README.md
Verified signature459317b
-
Create README.md
Verified signature5b78cf1
-
Upload feature extractor
Verified signaturee6b6cce -
Upload model
Verified signature083f870 -
initial commit
Verified signatureae6137a