forked from phoenix/litellm-mirror
108 lines
No EOL
1.9 KiB
Markdown
108 lines
No EOL
1.9 KiB
Markdown
import Tabs from '@theme/Tabs';
|
|
import TabItem from '@theme/TabItem';
|
|
|
|
# Audio Transcription
|
|
|
|
Use this to loadbalance across Azure + OpenAI.
|
|
|
|
## Quick Start
|
|
|
|
```python
|
|
from litellm import transcription
|
|
import os
|
|
|
|
# set api keys
|
|
os.environ["OPENAI_API_KEY"] = ""
|
|
audio_file = open("/path/to/audio.mp3", "rb")
|
|
|
|
response = transcription(model="whisper", file=audio_file)
|
|
|
|
print(f"response: {response}")
|
|
```
|
|
|
|
## Proxy Usage
|
|
|
|
### Add model to config
|
|
|
|
|
|
<Tabs>
|
|
<TabItem value="openai" label="OpenAI">
|
|
|
|
```yaml
|
|
model_list:
|
|
- model_name: whisper
|
|
litellm_params:
|
|
model: whisper-1
|
|
api_key: os.environ/OPENAI_API_KEY
|
|
model_info:
|
|
mode: audio_transcription
|
|
|
|
general_settings:
|
|
master_key: sk-1234
|
|
```
|
|
</TabItem>
|
|
<TabItem value="openai+azure" label="OpenAI + Azure">
|
|
|
|
```yaml
|
|
model_list:
|
|
- model_name: whisper
|
|
litellm_params:
|
|
model: whisper-1
|
|
api_key: os.environ/OPENAI_API_KEY
|
|
model_info:
|
|
mode: audio_transcription
|
|
- model_name: whisper
|
|
litellm_params:
|
|
model: azure/azure-whisper
|
|
api_version: 2024-02-15-preview
|
|
api_base: os.environ/AZURE_EUROPE_API_BASE
|
|
api_key: os.environ/AZURE_EUROPE_API_KEY
|
|
model_info:
|
|
mode: audio_transcription
|
|
|
|
general_settings:
|
|
master_key: sk-1234
|
|
```
|
|
|
|
</TabItem>
|
|
</Tabs>
|
|
|
|
### Start proxy
|
|
|
|
```bash
|
|
litellm --config /path/to/config.yaml
|
|
|
|
# RUNNING on http://0.0.0.0:8000
|
|
```
|
|
|
|
### Test
|
|
|
|
<Tabs>
|
|
<TabItem value="curl" label="Curl">
|
|
|
|
```bash
|
|
curl --location 'http://0.0.0.0:8000/v1/audio/transcriptions' \
|
|
--header 'Authorization: Bearer sk-1234' \
|
|
--form 'file=@"/Users/krrishdholakia/Downloads/gettysburg.wav"' \
|
|
--form 'model="whisper"'
|
|
```
|
|
|
|
</TabItem>
|
|
<TabItem value="openai" label="OpenAI">
|
|
|
|
```python
|
|
from openai import OpenAI
|
|
client = openai.OpenAI(
|
|
api_key="sk-1234",
|
|
base_url="http://0.0.0.0:8000"
|
|
)
|
|
|
|
|
|
audio_file = open("speech.mp3", "rb")
|
|
transcript = client.audio.transcriptions.create(
|
|
model="whisper",
|
|
file=audio_file
|
|
)
|
|
```
|
|
</TabItem>
|
|
</Tabs> |