Instructions to use TheAIchemist13/whisper-tiny-hi-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheAIchemist13/whisper-tiny-hi-model with Transformers:

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

pipe = pipeline("text-generation", model="TheAIchemist13/whisper-tiny-hi-model")

# Load model directly
from transformers import AutoProcessor, AutoModelForSeq2SeqLM

processor = AutoProcessor.from_pretrained("TheAIchemist13/whisper-tiny-hi-model")
model = AutoModelForSeq2SeqLM.from_pretrained("TheAIchemist13/whisper-tiny-hi-model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheAIchemist13/whisper-tiny-hi-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheAIchemist13/whisper-tiny-hi-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheAIchemist13/whisper-tiny-hi-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheAIchemist13/whisper-tiny-hi-model

SGLang

How to use TheAIchemist13/whisper-tiny-hi-model 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 "TheAIchemist13/whisper-tiny-hi-model" \
    --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": "TheAIchemist13/whisper-tiny-hi-model",
		"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 "TheAIchemist13/whisper-tiny-hi-model" \
        --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": "TheAIchemist13/whisper-tiny-hi-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheAIchemist13/whisper-tiny-hi-model with Docker Model Runner:
```
docker model run hf.co/TheAIchemist13/whisper-tiny-hi-model
```

TheAIchemist13 commited on Oct 3, 2023

Commit

7f3b454

1 Parent(s): e411293

Uploaded 2 files

Browse files

Files changed (2) hide show

config.json +14 -27
preprocessor_config.json +0 -0

config.json CHANGED Viewed

@@ -1,10 +1,10 @@
 {
-  "_name_or_path": "gramvaani_whisper-tiny-hi/",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
   "architectures": [
-    "PoptorchPipelinedWhisperForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
   "begin_suppress_tokens": [
@@ -13,32 +13,19 @@
   ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
-  "d_model": 384,
-  "decoder_attention_heads": 6,
-  "decoder_ffn_dim": 1536,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 4,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 6,
-  "encoder_ffn_dim": 1536,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 4,
   "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      50306
-    ],
-    [
-      2,
-      50359
-    ],
-    [
-      3,
-      50363
-    ]
-  ],
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
@@ -51,14 +38,14 @@
   "max_source_positions": 1500,
   "max_target_positions": 448,
   "model_type": "whisper",
-  "num_hidden_layers": 4,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
   "suppress_tokens": [],
-  "torch_dtype": "float16",
-  "transformers_version": "4.29.2",
-  "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

 {
+  "_name_or_path": "openai/whisper-small",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
   "architectures": [
+    "WhisperForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
   "begin_suppress_tokens": [
   ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
   "eos_token_id": 50257,
+  "forced_decoder_ids": null,
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
   "max_source_positions": 1500,
   "max_target_positions": 448,
   "model_type": "whisper",
+  "num_hidden_layers": 12,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
   "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

preprocessor_config.json CHANGED Viewed

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