Skip to content

GitLab

"...git@developer.sourcefind.cn:chenpangpang/transformers.git" did not exist on "d70fab8b2062526e9c2c60196421a8bc96c7df03"
Unverified Commit e118db15 authored by Patrick von Platen's avatar Patrick von Platen Committed by GitHub
Browse files

Update README.md

parent 01b14669
Show whitespace changes
Inline Side-by-side
Showing with 24 additions and 13 deletions
examples/pytorch/speech-recognition/README.md
View file @ e118db15
...@@ -113,19 +113,30 @@ of **0.36**. ...@@ -113,19 +113,30 @@ of **0.36**.
### Examples ### Examples
In the following a couple of demonstration fine-tuning runs are listed. The following tables present a couple of example runs on the most popular speech-recognition datasets.
It has been verified that the script works for the following datasets: The presented performances are by no means optimal as no hyper-parameter tuning was done. Nevertheless,
they can serve as a baseline to improve upon.
- [Common Voice](https://huggingface.co/datasets/common_voice)
- [Librispeech](https://huggingface.co/datasets/librispeech_asr)
- [TIMIT](https://huggingface.co/datasets/timit_asr) - [TIMIT](https://huggingface.co/datasets/timit_asr)
| Dataset | Dataset Config | Pretrained Model | Word error rate on eval | GPU setup | Training time | Fine-tuned Model & Logs | | Dataset | Dataset Config | Pretrained Model | Word error rate on eval | GPU setup | Training time | Fine-tuned Model & Logs | Command to reproduce |
|-------|------------------------------|-------------|---------------|---------------|----------------------|-------------| |-------|------------------------------|-------------|---------------|---------------|----------------------|-------------| -------------|
| [Librispeech](https://huggingface.co/datasets/librispeech_asr)| `"clean"` - `"train.100"` | [facebook/wav2vec2-large-lv60](https://huggingface.co/facebook/wav2vec2-large-lv60) | 0.042 | 8 GPU V100 | 1h30min | [here](https://huggingface.co/patrickvonplaten/wav2vec2-librispeech-clean-100h-demo-dist) | | [TIMIT](https://huggingface.co/datasets/timit_asr)| - | [wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) | 0.21 | 1 GPU TITAN RTX | 32min | [here](https://huggingface.co/patrickvonplaten/wav2vec2-base-timit-fine-tuned) | [run.sh](https://huggingface.co/patrickvonplaten/wav2vec2-base-timit-fine-tuned/blob/main/run.sh) |
| [Librispeech](https://huggingface.co/datasets/librispeech_asr)| `"clean"` - `"train.100"` | [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) | 0.088 | 8 GPU V100 | 1h30min | [here](https://huggingface.co/patrickvonplaten/hubert-librispeech-clean-100h-demo-dist) | | [TIMIT](https://huggingface.co/datasets/timit_asr)| - | [wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) | 0.21 | 1 GPU TITAN RTX | 32min | [here](https://huggingface.co/patrickvonplaten/wav2vec2-base-timit-fine-tuned) | [run.sh](https://huggingface.co/patrickvonplaten/wav2vec2-base-timit-fine-tuned/blob/main/run.sh) |
| [Common Voice](https://huggingface.co/datasets/common_voice)| `"tr"` | [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) | 0.36 | 8 GPU V100 | 18min | [here](https://huggingface.co/patrickvonplaten/wav2vec2-common_voice-tr-demo-dist) | | [TIMIT](https://huggingface.co/datasets/timit_asr)| - | [unispeech-large-1500h-cv](https://huggingface.co/microsoft/unispeech-large-1500h-cv) | 0.22 | 1 GPU TITAN RTX | 35min | [here](https://huggingface.co/patrickvonplaten/unispeech-large-1500h-cv-timit) | [run.sh](https://huggingface.co/patrickvonplaten/unispeech-large-1500h-cv-timit/blob/main/run.sh) |
| [Common Voice](https://huggingface.co/datasets/common_voice)| `"tr"` | [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) | 0.35 | 1 GPU V100 | 1h20min | [here](https://huggingface.co/patrickvonplaten/wav2vec2-common_voice-tr-demo) | | [TIMIT](https://huggingface.co/datasets/timit_asr)| - | [asapp/sew-mid-100k](https://huggingface.co/asapp/sew-mid-100k) | 0.30 | 1 GPU TITAN RTX | 28min | [here](https://huggingface.co/patrickvonplaten/sew-small-100k-timit) | [run.sh](https://huggingface.co/patrickvonplaten/sew-small-100k-timit/blob/main/run.sh) |
| [TIMIT](https://huggingface.co/datasets/timit_asr)| - | [wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) | 0.21 | 1 GPU TITAN RTX | 32min | [here](https://huggingface.co/patrickvonplaten/wav2vec2-base-timit-fine-tuned) |
| [TIMIT](https://huggingface.co/datasets/timit_asr)| - | [unispeech-large-1500h-cv](https://huggingface.co/microsoft/unispeech-large-1500h-cv) | 0.22 | 1 GPU TITAN RTX | 35min | [here](https://huggingface.co/patrickvonplaten/unispeech-large-1500h-cv-timit) | - [Librispeech](https://huggingface.co/datasets/librispeech_asr)
| [TIMIT](https://huggingface.co/datasets/timit_asr)| - | [unispeech-sat-base](https://huggingface.co/microsoft/unispeech-sat-base) | 0.41 | 1 GPU TITAN RTX | 32min | [here](https://huggingface.co/patrickvonplaten/unispeech-sat-base-timit-ft) |
| Dataset | Dataset Config | Pretrained Model | Word error rate on eval | GPU setup | Training time | Fine-tuned Model & Logs | Command to reproduce |
|-------|------------------------------|-------------|---------------|---------------|----------------------|-------------| -------------|
| [Librispeech](https://huggingface.co/datasets/librispeech_asr)| `"clean"` - `"train.100"` | [facebook/wav2vec2-large-lv60](https://huggingface.co/facebook/wav2vec2-large-lv60) | 0.042 | 8 GPU V100 | 1h30min | [here](https://huggingface.co/patrickvonplaten/wav2vec2-librispeech-clean-100h-demo-dist) | [run.sh](https://huggingface.co/patrickvonplaten/wav2vec2-librispeech-clean-100h-demo-dist/blob/main/run.sh) |
| [Librispeech](https://huggingface.co/datasets/librispeech_asr)| `"clean"` - `"train.100"` | [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) | 0.088 | 8 GPU V100 | 1h30min | [here](https://huggingface.co/patrickvonplaten/hubert-librispeech-clean-100h-demo-dist) | [run.sh](https://huggingface.co/patrickvonplaten/hubert-librispeech-clean-100h-demo-dist/blob/main/run.sh) |
| [Librispeech](https://huggingface.co/datasets/librispeech_asr)| `"clean"` - `"train.100"` | [asapp/sew-mid-100k](https://huggingface.co/asapp/sew-mid-100k) | 0.167 | 8 GPU V100 | 54min | [here](https://huggingface.co/patrickvonplaten/sew-mid-100k-librispeech-clean-100h-ft) | [run.sh](https://huggingface.co/patrickvonplaten/sew-mid-100k-librispeech-clean-100h-ft/blob/main/run.sh) |
- [Common Voice](https://huggingface.co/datasets/common_voice)
| Dataset | Dataset Config | Pretrained Model | Word error rate on eval | GPU setup | Training time | Fine-tuned Model & Logs | Command to reproduce |
|-------|------------------------------|-------------|---------------|---------------|----------------------|-------------| -------------|
| [Common Voice](https://huggingface.co/datasets/common_voice)| `"tr"` | [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) | 0.36 | 8 GPU V100 | 18min | [here](https://huggingface.co/patrickvonplaten/wav2vec2-common_voice-tr-demo-dist) | [run.sh](https://huggingface.co/patrickvonplaten/wav2vec2-common_voice-tr-demo-dist/blob/main/run_dist.sh) |
| [Common Voice](https://huggingface.co/datasets/common_voice)| `"tr"` | [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) | 0.35 | 1 GPU V100 | 1h20min | [here](https://huggingface.co/patrickvonplaten/wav2vec2-common_voice-tr-demo) | [run.sh](https://huggingface.co/patrickvonplaten/wav2vec2-common_voice-tr-demo/blob/main/run.sh) |
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment