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 ·
d9ecd5a
1
Parent(s): cfaec9e
README.md
CHANGED
|
@@ -27,22 +27,22 @@ model-index:
|
|
| 27 |
value: 54.97
|
| 28 |
name: Test WER
|
| 29 |
description: Word Error Rate
|
| 30 |
-
- type: mer
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
- type: wil
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
- type: wip
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
- type: cer
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
|
| 47 |
# - task:
|
| 48 |
# type: automatic-speech-recognition
|
|
|
|
| 27 |
value: 54.97
|
| 28 |
name: Test WER
|
| 29 |
description: Word Error Rate
|
| 30 |
+
# - type: mer
|
| 31 |
+
# value: 47.86
|
| 32 |
+
# name: Test MER
|
| 33 |
+
# description: Match Error Rate
|
| 34 |
+
# - type: wil
|
| 35 |
+
# value: 66.83
|
| 36 |
+
# name: Test WIL
|
| 37 |
+
# description: Word Information Lost
|
| 38 |
+
# - type: wip
|
| 39 |
+
# value: 33.16
|
| 40 |
+
# name: Test WIP
|
| 41 |
+
# description: Word Information Preserved
|
| 42 |
+
# - type: cer
|
| 43 |
+
# value: 30.23
|
| 44 |
+
# name: Test CER
|
| 45 |
+
# description: Character Error Rate
|
| 46 |
|
| 47 |
# - task:
|
| 48 |
# type: automatic-speech-recognition
|