mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
58a96e5b68
* WIP: Support exporting to ONNX format * Minor fixes. * Combine encoder/decoder/joiner into a single file. * Revert merging three onnx models into a single one. It's quite time consuming to extract a sub-graph from the combined model. For instance, it takes more than one hour to extract the encoder model. * Update CI to test ONNX models. * Decode with exported models. * Fix typos. * Add more doc. * Remove ncnn as it is not fully tested yet. * Fix as_strided for streaming conformer.
26 lines
672 B
Plaintext
26 lines
672 B
Plaintext
# Usage: grep -v '^#' requirements-ci.txt | xargs -n 1 -L 1 pip install
|
|
# dependencies for GitHub actions
|
|
#
|
|
# See https://github.com/actions/setup-python#caching-packages-dependencies
|
|
|
|
# numpy 1.20.x does not support python 3.6
|
|
numpy==1.19
|
|
pytest==7.1.0
|
|
graphviz==0.19.1
|
|
|
|
-f https://download.pytorch.org/whl/cpu/torch_stable.html torch==1.10.0+cpu
|
|
-f https://download.pytorch.org/whl/cpu/torch_stable.html torchaudio==0.10.0+cpu
|
|
|
|
-f https://k2-fsa.org/nightly/ k2==1.15.1.dev20220426+cpu.torch1.10.0
|
|
|
|
git+https://github.com/lhotse-speech/lhotse
|
|
kaldilm==1.11
|
|
kaldialign==0.2
|
|
sentencepiece==0.1.96
|
|
tensorboard==2.8.0
|
|
typeguard==2.13.3
|
|
multi_quantization
|
|
|
|
onnx
|
|
onnxruntime
|