Automatic Speech Recognition
Transformers
PyTorch
whisper
audio
speech
wav2vec2
Eval Results (legacy)
Instructions to use devasheeshG/whisper_medium_fp16_transformers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use devasheeshG/whisper_medium_fp16_transformers with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="devasheeshG/whisper_medium_fp16_transformers")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("devasheeshG/whisper_medium_fp16_transformers") model = AutoModelForSpeechSeq2Seq.from_pretrained("devasheeshG/whisper_medium_fp16_transformers", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
116860c
1
Parent(s): d9ecd5a
README.md
CHANGED
|
@@ -23,10 +23,10 @@ model-index:
|
|
| 23 |
args:
|
| 24 |
language: hi
|
| 25 |
metrics:
|
| 26 |
-
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
# - type: mer
|
| 31 |
# value: 47.86
|
| 32 |
# name: Test MER
|
|
|
|
| 23 |
args:
|
| 24 |
language: hi
|
| 25 |
metrics:
|
| 26 |
+
- wer:
|
| 27 |
+
value: 54.97
|
| 28 |
+
name: Test WER
|
| 29 |
+
description: Word Error Rate
|
| 30 |
# - type: mer
|
| 31 |
# value: 47.86
|
| 32 |
# name: Test MER
|