Text-to-Speech
Transformers
Safetensors
MLX
English
Hindi
llama
text-generation
tts
hindi
english
audio
speech
india
mlx-my-repo
text-generation-inference
4-bit precision
Instructions to use hashvibe007/Veena-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hashvibe007/Veena-mlx-4Bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="hashvibe007/Veena-mlx-4Bit")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("hashvibe007/Veena-mlx-4Bit") model = AutoModelForCausalLM.from_pretrained("hashvibe007/Veena-mlx-4Bit", device_map="auto") - MLX
How to use hashvibe007/Veena-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Veena-mlx-4Bit hashvibe007/Veena-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Upload special_tokens_map.json with huggingface_hub
Browse files- special_tokens_map.json +36 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<spk_kavya>",
|
| 4 |
+
"<spk_apsara>",
|
| 5 |
+
"<spk_agastya>",
|
| 6 |
+
"<spk_vinaya>",
|
| 7 |
+
"<spk_maitri>",
|
| 8 |
+
"<spk_charu>",
|
| 9 |
+
"<spk_ishana>",
|
| 10 |
+
"<spk_kyra>",
|
| 11 |
+
"<spk_mohini>",
|
| 12 |
+
"<spk_varun>",
|
| 13 |
+
"<spk_soumya>"
|
| 14 |
+
],
|
| 15 |
+
"bos_token": {
|
| 16 |
+
"content": "<|begin_of_text|>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"eos_token": {
|
| 23 |
+
"content": "<|eot_id|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"pad_token": {
|
| 30 |
+
"content": "<custom_token_7>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|