Instructions to use commotion/multilingual-5-speaker-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use commotion/multilingual-5-speaker-v1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="commotion/multilingual-5-speaker-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("commotion/multilingual-5-speaker-v1")
model = AutoModelForCausalLM.from_pretrained("commotion/multilingual-5-speaker-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use commotion/multilingual-5-speaker-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "commotion/multilingual-5-speaker-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "commotion/multilingual-5-speaker-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/commotion/multilingual-5-speaker-v1

SGLang

How to use commotion/multilingual-5-speaker-v1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "commotion/multilingual-5-speaker-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "commotion/multilingual-5-speaker-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "commotion/multilingual-5-speaker-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "commotion/multilingual-5-speaker-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use commotion/multilingual-5-speaker-v1 with Docker Model Runner:
```
docker model run hf.co/commotion/multilingual-5-speaker-v1
```

SankalpC10 commited on Mar 19

Commit

ed882ea

verified ·

1 Parent(s): 44aadb0

Upload tokenizer

Browse files

Files changed (4) hide show

.gitattributes +1 -0
special_tokens_map.json +28 -0
tokenizer.json +3 -0
tokenizer_config.json +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "additional_special_tokens": [
+    "<spk_tanya>",
+    "<spk_raj>",
+    "<spk_komal>"
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<custom_token_2>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<custom_token_7>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:55ba8d5ad400d8d1f2d7e97c6706b83ce3ad579c61364df77cbd238b92d7c956
+size 22850486

tokenizer_config.json ADDED Viewed

The diff for this file is too large to render. See raw diff