Downloads · 30 days
13
2% of all-time downloads
infinitejoy/wav2vec2-large-xls-r-300m-odia
wav2vec2-large-xls-r-300m-odia is a automatic speech recognition model from infinitejoy. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
13
2% of all-time downloads
All-time downloads
574
Public
Repo size
8.8 GB
Likes
0
Public
Click a slice to open those files.
.bin1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - OR dataset. It achieves the following results on the evaluation set:
python eval.py --model_id ./ --dataset mozilla-foundation/common_voice_7_0 --config as --split test --log_outputs
More information needed
More information needed
Training machine details
Training script
python run_speech_recognition_ctc.py \
--dataset_name="mozilla-foundation/common_voice_7_0" \
--model_name_or_path="facebook/wav2vec2-xls-r-300m" \
--dataset_config_name="or" \
--output_dir="./wav2vec2-large-xls-r-300m-odia" \
--overwrite_output_dir \
--num_train_epochs="120" \
--per_device_train_batch_size="16" \
--per_device_eval_batch_size="16" \
--gradient_accumulation_steps="2" \
--learning_rate="7.5e-5" \
--warmup_steps="500" \
--length_column_name="input_length" \
--evaluation_strategy="steps" \
--text_column_name="sentence" \
--chars_to_ignore , ? . ! \- \; \: \" “ % ‘ ” � — \’ … \– \' \’ \– \
--save_steps="500" \
--eval_steps="500" \
--logging_steps="100" \
--layerdrop="0.0" \
--activation_dropout="0.1" \
--save_total_limit="3" \
--freeze_feature_encoder \
--feat_proj_dropout="0.0" \
--mask_time_prob="0.75" \
--mask_time_length="10" \
--mask_feature_prob="0.25" \
--mask_feature_length="64" \
--gradient_checkpointing \
--use_auth_token \
--fp16 \
--group_by_length \
--do_train --do_eval \
--push_to_hub
The following hyperparameters were used during training:
| eval_loss | eval_wer | eval_runtime | eval_samples_per_second | eval_steps_per_second | epoch | |
|---|---|---|---|---|---|---|
| 0 | 3.35224 | 0.998972 | 5.0475 | 22.189 | 1.387 | 29.41 |
| 1 | 1.33679 | 0.938335 | 5.0633 | 22.12 | 1.382 | 58.82 |
| 2 | 0.737202 | 0.957862 | 5.0913 | 21.998 | 1.375 | 88.24 |
| 3 | 0.658212 | 0.96814 | 5.0953 | 21.981 | 1.374 | 117.65 |
| 4 | 0.658 | 0.9712 | 5.0953 | 22.115 | 1.382 | 120 |