fba5e67d5e
- Introduce unified AMP helpers (create_grad_scaler, torch_autocast) to handle deprecations in PyTorch ≥2.3.0 - Replace direct uses of torch.cuda.amp.GradScaler and torch.cuda.amp.autocast with the new utilities across all training and inference scripts - Update all torch.load calls to include weights_only=False for compatibility with newer PyTorch versions
Introduction
This recipe contains various different ASR models trained with Aishell2.
In AISHELL-2, 1000 hours of clean read-speech data from iOS is published, which is free for academic usage. On top of AISHELL-2 corpus, an improved recipe is developed and released, containing key components for industrial applications, such as Chinese word segmentation, flexible vocabulary expension and phone set transformation etc. Pipelines support various state-of-the-art techniques, such as time-delayed neural networks and Lattic-Free MMI objective funciton. In addition, we also release dev and test data from other channels (Android and Mic).
(From AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale)
./RESULTS.md contains the latest results.
Transducers
There are various folders containing the name transducer in this folder.
The following table lists the differences among them.
| Encoder | Decoder | Comment | |
|---|---|---|---|
pruned_transducer_stateless5 |
Conformer(modified) | Embedding + Conv1d | same as pruned_transducer_stateless5 in librispeech recipe |
The decoder in transducer_stateless is modified from the paper
Rnn-Transducer with Stateless Prediction Network.
We place an additional Conv1d layer right after the input embedding layer.