Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,22 @@
|
|
| 2 |
license: mit
|
| 3 |
language:
|
| 4 |
- en
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
# Speech Recognition AI: Fine-Tuned Whisper and Wav2Vec2 for Real-Time Audio
|
|
@@ -25,7 +41,7 @@ This is a fine-tuned version of [OpenAI's Whisper small model](https://huggingfa
|
|
| 25 |
## Installation
|
| 26 |
Clone the repository and install the dependencies:
|
| 27 |
```bash
|
| 28 |
-
git clone https://github.com/
|
| 29 |
cd speech-model
|
| 30 |
pip install -r requirements.txt
|
| 31 |
```
|
|
|
|
| 2 |
license: mit
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
+
datasets:
|
| 6 |
+
- facebook/multilingual_librispeech
|
| 7 |
+
metrics:
|
| 8 |
+
- character
|
| 9 |
+
base_model:
|
| 10 |
+
- openai/whisper-small
|
| 11 |
+
- facebook/wav2vec2-base-960h
|
| 12 |
+
pipeline_tag: automatic-speech-recognition
|
| 13 |
+
library_name: transformers
|
| 14 |
+
tags:
|
| 15 |
+
- code
|
| 16 |
+
- audio
|
| 17 |
+
- speech-recognition
|
| 18 |
+
- whisper
|
| 19 |
+
- wav2vec2
|
| 20 |
+
- pytorch
|
| 21 |
---
|
| 22 |
|
| 23 |
# Speech Recognition AI: Fine-Tuned Whisper and Wav2Vec2 for Real-Time Audio
|
|
|
|
| 41 |
## Installation
|
| 42 |
Clone the repository and install the dependencies:
|
| 43 |
```bash
|
| 44 |
+
git clone https://github.com/bniladridas/speech-model.git
|
| 45 |
cd speech-model
|
| 46 |
pip install -r requirements.txt
|
| 47 |
```
|