Downloads · 30 days
4
2% of all-time downloads
wav2vec2-aed-switchboard
esc-bench/wav2vec2-aed-switchboard
wav2vec2-aed-switchboard is a automatic speech recognition model from esc-bench. Use it when you need speech turned into text. It is set up for transformers.
All-time downloads
220
Public
Repo size
2.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.msgpack2.4 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- speech-encoder-decoder
- Access
- Public
- Created
- Sep 30, 2022
- Updated
- Oct 24, 2022
- SHA
- 6c13e97f
Datasets
Model card
From the Hugging Face model README
To reproduce this run, execute:
#!/usr/bin/env bash
python run_flax_speech_recognition_seq2seq.py \
--dataset_name="esb/datasets" \
--model_name_or_path="esb/wav2vec2-aed-pretrained" \
--dataset_config_name="switchboard" \
--output_dir="./" \
--wandb_name="wav2vec2-aed-switchboard" \
--wandb_project="wav2vec2-aed" \
--per_device_train_batch_size="8" \
--per_device_eval_batch_size="2" \
--learning_rate="1e-4" \
--warmup_steps="500" \
--logging_steps="25" \
--max_steps="50001" \
--eval_steps="10000" \
--save_steps="10000" \
--generation_max_length="40" \
--generation_num_beams="1" \
--final_generation_max_length="260" \
--final_generation_num_beams="5" \
--generation_length_penalty="0.8" \
--overwrite_output_dir \
--gradient_checkpointing \
--freeze_feature_encoder \
--predict_with_generate \
--do_eval \
--do_train \
--do_predict \
--push_to_hub \
--use_auth_token
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- speech-encoder-decoder
- Languages
- en
- Created
- Sep 30, 2022
- Updated
- Oct 24, 2022