Instructions to use danielizham/whisper-small-ar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use danielizham/whisper-small-ar with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="danielizham/whisper-small-ar")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("danielizham/whisper-small-ar") model = AutoModelForSpeechSeq2Seq.from_pretrained("danielizham/whisper-small-ar", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
8bb51d2
1
Parent(s): 95fb46e
Training in progress, step 12500
Browse files
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 967102601
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5af933baa414d4abc6e74d22f0b1395e785082345eb3a9456295b6739531e1ec
|
| 3 |
size 967102601
|
wandb/run-20230525_235750-fyg3cg7f/files/wandb-summary.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval/loss": 0.
|
|
|
|
| 1 |
+
{"eval/loss": 0.851005494594574, "eval/wer": 57.976000000000006, "eval/runtime": 770.7846, "eval/samples_per_second": 13.545, "_timestamp": 1685785343.9848542, "_runtime": 737073.5388462543, "_step": 549}
|
wandb/run-20230525_235750-fyg3cg7f/run-fyg3cg7f.wandb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04d43077893f2284f29d2e4959f7d26aceac23cad5a7822a2b780f377b3810cb
|
| 3 |
+
size 68255850
|