SpeechMix
Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together.
Implementation of:
Large-Scale Self- and Semi-Supervised Learning for Speech Translation - ACL2021
Multilingual Speech Translation with Efficient Finetuning of Pretrained Models - ACL2021
Lightweight Adapter Tuning for Multilingual Speech Translation - Interspeech 2021
Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task - ACL2021
A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks - ICASSP 2021
Installation
pip install
pip install speechmix
Build from source
git clone and cd into this project.
pip install -e .
Name the project(!important)
WANDB_PROJECT=amazing
base
python train.py --speech_model_config wav2vec2 \
--nlp_model_config facebook/bart-base \
--SpeechMixEED \
--dataset librispeech_asr \
--field clean \
--train_split train.100 \
--test_split validation \
--batch 3 \
--grad_accum 20 \
--epoch 30 \
--worker 15 \
--share_layer_ratio 0 \
--down_scale 2 \
--lr 4e-5 \
--warmup_steps 500 \
--wandb \
--notes base
Metadata
Release files for speechmix 0.0.32
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| speechmix-0.0.32.tar.gz | 18.1 kB | Without provenance | Details for speechmix-0.0.32.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| speechmix-0.0.32-py3-none-any.whl | Python 3 | none | any | Details for speechmix-0.0.32-py3-none-any.whl |
Total release size: 31.3 kB
Release files / speechmix-0.0.32.tar.gz
| Download URL | speechmix-0.0.32.tar.gz |
|---|---|
| Size | 18.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
6095e3e5b392c90b68d5bf5b7258374d795879ca2ac92b74f19cb0e81460e058
|
|
BLAKE2b-256 checksum How to use checksums |
04e08453be39c4d6e137addaa530d3074ff8de2111a826dc82d88df46b4942a7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.8.0 pkginfo/1.8.2 readme-renderer/33.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.8 tqdm/4.62.3 importlib-metadata/4.11.1 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.8.9
|
Release files / speechmix-0.0.32-py3-none-any.whl
| Download URL | speechmix-0.0.32-py3-none-any.whl |
|---|---|
| Size | 13.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
93b82a6e19e82f2faf3f4378c68d64c0856aeeaa002b0934bb7101235215152a
|
|
BLAKE2b-256 checksum How to use checksums |
388b58a8493898f1f2d1900ecb0175f62f09780886ff4181ae13d6dc8f05c334
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.8.0 pkginfo/1.8.2 readme-renderer/33.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.8 tqdm/4.62.3 importlib-metadata/4.11.1 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.8.9
|
Security for speechmix 0.0.32
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.