Downloads · 30 days
10
18% of all-time downloads
wav2vec2-base-100h-13K-steps
patrickvonplaten/wav2vec2-base-100h-13K-steps
wav2vec2-base-100h-13K-steps is a automatic speech recognition model from patrickvonplaten. Use it when you need speech turned into text. It is set up for transformers.
Fine-tuning of wav2vec2-base on 100h of Librispeech training data. Results on "clean" data are very similar to the ones of the official model. However, the result on "other" is significantly worse - the model seems to…
All-time downloads
55
Public
Repo size
755 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin378 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- wav2vec2
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Mar 3, 2021
- SHA
- 408690c6
Model card
From the Hugging Face model README
Fine-tuning of wav2vec2-base on 100h of Librispeech training data. Results on "clean" data are very similar to the ones of the official model. However, the result on "other" is significantly worse - the model seems to have overfitting to the "clean" data.
Model was trained on librispeech-clean-train.100 with following hyper-parameters:
- 2 GPUs Titan RTX
- Total update steps 13000
- Batch size per GPU: 32 corresponding to a total batch size of ca. ~1500 seconds
- Adam with linear decaying learning rate with 3000 warmup steps
- dynamic grouping for batch
- fp16
- attention_mask was not used during training
Result (WER) on Librispeech test:
| "clean" | "other" |
|---|---|
| 6.5 | 18.7 |
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Created
- Mar 2, 2022
- Updated
- Mar 3, 2021