Commit
•
63c7357
1
Parent(s):
56de3dd
Update README.md
Browse files
README.md
CHANGED
|
@@ -87,7 +87,7 @@ processor = Wav2Vec2Processor.from_pretrained("PereLluis13/wav2vec2-large-xlsr-5
|
|
| 87 |
model = Wav2Vec2ForCTC.from_pretrained("PereLluis13/wav2vec2-large-xlsr-53-greek")
|
| 88 |
model.to("cuda")
|
| 89 |
|
| 90 |
-
chars_to_ignore_regex = '[
|
| 91 |
|
| 92 |
|
| 93 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
|
@@ -137,6 +137,6 @@ The Common Voice `train`, `validation`, and CSS10 datasets were used for trainin
|
|
| 137 |
return batch
|
| 138 |
```
|
| 139 |
|
| 140 |
-
As suggested by Florian Zimmermeister.
|
| 141 |
|
| 142 |
The script used for training can be found in [run_common_voice.py](examples/research_projects/wav2vec2/run_common_voice.py), still pending of PR. The only changes are to `speech_file_to_array_fn`. Batch size was kept at 32 (using `gradient_accumulation_steps`) using one of the [OVH](https://www.ovh.com/) machines, with a V100 GPU (thank you very much [OVH](https://www.ovh.com/)). The model trained for 40 epochs, the first 20 with the `train+validation` splits, and then `extra` split was added with the data from CSS10 at the 20th epoch.
|
|
|
|
| 87 |
model = Wav2Vec2ForCTC.from_pretrained("PereLluis13/wav2vec2-large-xlsr-53-greek")
|
| 88 |
model.to("cuda")
|
| 89 |
|
| 90 |
+
chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\�]'
|
| 91 |
|
| 92 |
|
| 93 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
|
|
|
| 137 |
return batch
|
| 138 |
```
|
| 139 |
|
| 140 |
+
As suggested by [Florian Zimmermeister](https://github.com/flozi00).
|
| 141 |
|
| 142 |
The script used for training can be found in [run_common_voice.py](examples/research_projects/wav2vec2/run_common_voice.py), still pending of PR. The only changes are to `speech_file_to_array_fn`. Batch size was kept at 32 (using `gradient_accumulation_steps`) using one of the [OVH](https://www.ovh.com/) machines, with a V100 GPU (thank you very much [OVH](https://www.ovh.com/)). The model trained for 40 epochs, the first 20 with the `train+validation` splits, and then `extra` split was added with the data from CSS10 at the 20th epoch.
|