Automatic Speech Recognition
Transformers
Safetensors
English
whisper
audio
hallucination
weight-editing
Instructions to use erickvs/whisper-tiny.en-hand-edited with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use erickvs/whisper-tiny.en-hand-edited with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="erickvs/whisper-tiny.en-hand-edited")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("erickvs/whisper-tiny.en-hand-edited") model = AutoModelForSpeechSeq2Seq.from_pretrained("erickvs/whisper-tiny.en-hand-edited", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Card: use the canonical Patreon link
Browse files
README.md
CHANGED
|
@@ -193,7 +193,7 @@ that went wrong, is in the experiment notes.
|
|
| 193 |
|
| 194 |
These experiments run on one laptop, but the AI agents that make and audit the edits cost real money: the three editors behind this
|
| 195 |
release used about 830,000 tokens. If you'd like more models fixed by hand like this one, published with their full results and
|
| 196 |
-
limits, you can **[support the experiments on Patreon](https://www.patreon.com/c/ErickVazquezSantillan
|
| 197 |
for the tokens behind the next ones.
|
| 198 |
|
| 199 |
## Credits and license
|
|
|
|
| 193 |
|
| 194 |
These experiments run on one laptop, but the AI agents that make and audit the edits cost real money: the three editors behind this
|
| 195 |
release used about 830,000 tokens. If you'd like more models fixed by hand like this one, published with their full results and
|
| 196 |
+
limits, you can **[support the experiments on Patreon](https://www.patreon.com/c/ErickVazquezSantillan)**. It pays
|
| 197 |
for the tokens behind the next ones.
|
| 198 |
|
| 199 |
## Credits and license
|