Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use sgangireddy/whisper-medium-mls-fr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sgangireddy/whisper-medium-mls-fr with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="sgangireddy/whisper-medium-mls-fr")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("sgangireddy/whisper-medium-mls-fr") model = AutoModelForSpeechSeq2Seq.from_pretrained("sgangireddy/whisper-medium-mls-fr") - Notebooks
- Google Colab
- Kaggle
Commit ·
0743f38
1
Parent(s): a7b64d6
results json files
Browse files- .gitignore +1 -0
- eval_results.json +8 -0
- train_results.json +7 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.1239842027425766,
|
| 4 |
+
"eval_runtime": 3981.693,
|
| 5 |
+
"eval_samples_per_second": 0.609,
|
| 6 |
+
"eval_steps_per_second": 0.019,
|
| 7 |
+
"eval_wer": 6.497245494665325
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.1424,
|
| 4 |
+
"train_runtime": 14400.0033,
|
| 5 |
+
"train_samples_per_second": 3.462,
|
| 6 |
+
"train_steps_per_second": 0.054
|
| 7 |
+
}
|