Text-to-Speech
Transformers
Safetensors
qwen3
text-generation
speech
tts
voice
text-generation-inference
Instructions to use SPRINGLab/Indic-Mio with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SPRINGLab/Indic-Mio with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="SPRINGLab/Indic-Mio")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SPRINGLab/Indic-Mio") model = AutoModelForCausalLM.from_pretrained("SPRINGLab/Indic-Mio") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- .gitattributes +4 -0
- README.md +19 -6
- samples/sample1.wav +3 -0
- samples/sample2.wav +3 -0
- samples/sample3.wav +3 -0
- samples/sample4.wav +3 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
samples/sample1.wav filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
samples/sample2.wav filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
samples/sample3.wav filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
samples/sample4.wav filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -33,6 +33,23 @@ tags:
|
|
| 33 |
- tts
|
| 34 |
- voice
|
| 35 |
licence: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
---
|
| 37 |
|
| 38 |
# Model Card for Indic-Mio
|
|
@@ -61,19 +78,15 @@ A word can be stressed by using asterisks(*) around it. For example: `No! I coul
|
|
| 61 |
Install [vllm](https://github.com/vllm-project/vllm) and set up [MioTTS-Inference](https://github.com/Aratako/MioTTS-Inference).
|
| 62 |
|
| 63 |
```bash
|
| 64 |
-
vllm serve SPRINGLab/Indic-Mio --
|
| 65 |
```
|
| 66 |
|
| 67 |
```bash
|
| 68 |
cd MioTTS-Inference
|
| 69 |
-
|
| 70 |
-
MIOTTS_LLM_BASE_URL=http://localhost:8000/v1 \
|
| 71 |
-
python run_server.py --host 0.0.0.0 --port 8001
|
| 72 |
```
|
| 73 |
|
| 74 |
```bash
|
| 75 |
-
GRADIO_SERVER_PORT=7861 \
|
| 76 |
-
MIOTTS_API_BASE=http://127.0.0.1:8001 \
|
| 77 |
python run_gradio.py
|
| 78 |
```
|
| 79 |
|
|
|
|
| 33 |
- tts
|
| 34 |
- voice
|
| 35 |
licence: apache-2.0
|
| 36 |
+
datasets:
|
| 37 |
+
- ai4bharat/Rasa
|
| 38 |
+
- mythicinfinity/libritts_r
|
| 39 |
+
- ylacombe/expresso
|
| 40 |
+
widget:
|
| 41 |
+
- text: "प्लान तो बढ़िया है, but wait... Have you checked the hotel bookings? Last minute पे रूम मिलना is next to impossible on weekends."
|
| 42 |
+
output:
|
| 43 |
+
url: samples/sample1.wav
|
| 44 |
+
- text: "The rain hammered against the cold glass as Detective Morgan slammed the folder onto the table. 'I know you were there that night,' she said, her voice barely above a whisper. 'The question is — what did you see?'"
|
| 45 |
+
output:
|
| 46 |
+
url: samples/sample2.wav
|
| 47 |
+
- text: "જ્યારે પણ મને તેની સખત જરૂર હોય ત્યારે આ દુકાનમાં મદદ કરવા માટે ક્યારેય કોઈ હાજર નથી હોતું. <disgust>"
|
| 48 |
+
output:
|
| 49 |
+
url: samples/sample3.wav
|
| 50 |
+
- text: "இந்த கோயில்லயா உங்க கல்யாணம் நடந்துச்சு. <surprise>"
|
| 51 |
+
output:
|
| 52 |
+
url: samples/sample4.wav
|
| 53 |
---
|
| 54 |
|
| 55 |
# Model Card for Indic-Mio
|
|
|
|
| 78 |
Install [vllm](https://github.com/vllm-project/vllm) and set up [MioTTS-Inference](https://github.com/Aratako/MioTTS-Inference).
|
| 79 |
|
| 80 |
```bash
|
| 81 |
+
vllm serve SPRINGLab/Indic-Mio --gpu-memory-utilization 0.5
|
| 82 |
```
|
| 83 |
|
| 84 |
```bash
|
| 85 |
cd MioTTS-Inference
|
| 86 |
+
python run_server.py
|
|
|
|
|
|
|
| 87 |
```
|
| 88 |
|
| 89 |
```bash
|
|
|
|
|
|
|
| 90 |
python run_gradio.py
|
| 91 |
```
|
| 92 |
|
samples/sample1.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b331f7ea55e3ded2ba9c0d8b69466d773bd28a375fcff2524a85ba1a0054402
|
| 3 |
+
size 638612
|
samples/sample2.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:507f0ed0e63b502f81e6bb6e37d0b323a2292b13f72ba59832d11c5f5030b3be
|
| 3 |
+
size 1146644
|
samples/sample3.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dabec3c1a3fc8e3aebc8c188325e24cc3c6cd55bfd306d437a535dcd8a0e90c
|
| 3 |
+
size 504548
|
samples/sample4.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9869a3dffc14b2b762e2cab41276f1a625536b34f3668d611858e24f63a3189d
|
| 3 |
+
size 254060
|