remsky
8f86d60319
Merge pull request #145 from remsky/revert-92-v0.1.2-pre
...
Revert "Adds support for creating weighted voice combinations" (Implemented somewhat differently)
2025-02-09 22:42:43 -07:00
remsky
f11a6b3e2b
Revert "Adds support for creating weighted voice combinations"
2025-02-09 22:41:42 -07:00
remsky
d5709097e2
Merge pull request #92 from rvuyyuru2/v0.1.2-pre
...
Adds support for creating weighted voice combinations (reimplemented in v0.2.0)
2025-02-09 22:37:16 -07:00
remsky
00497f8872
Refactor: Consolidate PyTorch CPU and GPU backends into a single PyTorchBackend class; remove obsolete files
2025-01-25 13:33:42 -07:00
rvuyyuru2
6d717437c9
Renames service and expands Docker configuration
...
Updates the service name to 'InstaVoice' and introduces multiple server services to enhance scalability.
Modifies GPU resource allocation to use all available devices and adds an NGINX service for reverse proxy capabilities.
Simplifies the structure for better management of the API and UI services.
2025-01-25 21:55:53 +05:30
rvuyyuru2
44c62467ae
Adds support for creating weighted voice combinations
...
Implements a new method to parse weighted voice formulas and generate combined audio outputs based on specified weights.
This enhancement allows for more diverse audio generation by letting users specify multiple voices with respective weights, improving flexibility in voice management.
Updates voice processing logic in relevant API routes to handle weighted formulas seamlessly.
Fixes #123 (if applicable, replace with the actual issue reference)
2025-01-25 20:54:21 +05:30
remsky
3547d95ee6
-unified streaming implementation
2025-01-25 05:25:13 -07:00
remsky
90c8f11111
Add CPU and GPU startup scripts; update dependencies in pyproject.toml
2025-01-24 23:46:46 -07:00
remsky
9efb9db4d9
Fix: VoiceManager singleton instantiation
2025-01-24 05:30:56 -07:00
remsky
20658f9759
Performance: Adjust session timeout and GPU memory limit; minim voice pre-caching and improve singleton instance management
2025-01-24 05:01:38 -07:00
remsky
ee1f7cde18
Add async audio processing and semantic chunking support; flattened static audio trimming
2025-01-24 04:06:47 -07:00
remsky
31b5e33408
Multiarch support
2025-01-24 01:05:24 -07:00
remsky
44724b2035
Update README.md
2025-01-23 06:06:29 -07:00
remsky
c92045c598
Add Docker build scripts for CPU and GPU images, update Dockerfiles to include project files and adjust ONNX usage
2025-01-23 05:41:30 -07:00
remsky
8eb3525382
Refactor configuration and enhance web interface: update GPU settings, add speed control, and improve input handling for audio generation
2025-01-23 04:54:55 -07:00
remsky
ba577d348e
Enhance web player information, adjust text chunk size, update audio wave settings, and implement OpenAI model mappings
2025-01-23 04:11:31 -07:00
remsky
a8e6a3d2d9
Add badges for and adjust header styles for better layout
2025-01-23 02:10:01 -07:00
remsky
8e8f120a3e
Update configuration to disable local voice saving, enhance voice validation logic, and remove deprecated test file
2025-01-23 02:00:46 -07:00
remsky
df4cc5b4b2
-Adjust testing framework for new model
...
-Add web player support: include static file serving and HTML interface for TTS
2025-01-22 21:11:47 -07:00
remsky
66f46e82f9
Refactor ONNX GPU backend and phoneme generation: improve token handling, add chunk processing for audio generation, and initial introduce stitch options for audio chunks.
2025-01-22 17:43:38 -07:00
remsky
d50214d3be
Enable ONNX GPU support in Docker configurations and refactor model file handling
2025-01-22 05:00:38 -07:00
remsky
4a24be1605
Refactor model loading and configuration: update, adjust model loading device,. add async streaming examples and remove unused warmup service.
2025-01-22 02:33:29 -07:00
remsky
21bf810f97
Enhance model inference: update documentation, add model download scripts for PyTorch and ONNX, and refactor configuration handling
2025-01-21 21:44:21 -07:00
remsky
ab28a62e86
Refactor inference architecture: remove legacy TTS model, add ONNX and PyTorch backends, and introduce model configuration schemas
2025-01-20 22:42:29 -07:00
remsky
83c55ca735
Update ci.yml
2025-01-18 00:08:31 -07:00
remsky
dba8220627
Merge pull request #74 from richardr1126/master
...
Try to add AAC audio format w/ updated test
2025-01-17 23:37:54 -07:00
Richard Roberson
d51d861861
add AAC audio format and test
2025-01-17 21:43:10 -07:00
remsky
57f3cf6338
Update issue templates
2025-01-17 18:20:43 -07:00
remsky
fddafacaf0
Update issue templates
2025-01-17 18:17:21 -07:00
remsky
3788d592bf
Merge pull request #69 from fireblade2534/master
...
Fixed python tests so they run properly and cleaned up some unneeded …
2025-01-17 18:06:08 -07:00
Fireblade2534
9d84207c35
Added app to git ignore
2025-01-17 15:38:31 +00:00
Fireblade2534
eb556ec7d3
Fixed python tests so they run properly and cleaned up some unneeded files
2025-01-17 14:55:25 +00:00
remsky
7711c32fc2
Update README.md
2025-01-16 02:19:35 -07:00
remsky
8f0150a577
Merge pull request #51 from jteijema/update-UI-access
...
Update UI access with environment URL and PORT
2025-01-15 20:45:36 -07:00
remsky
746fd9be4b
Merge branch 'master' into update-UI-access
2025-01-15 20:44:54 -07:00
remsky
3acc654f10
Update README.md
2025-01-15 03:06:17 -07:00
remsky
ee0644f2ba
Update README.md
2025-01-15 03:00:42 -07:00
remsky
ceeea5ab43
Update README.md
2025-01-15 02:54:24 -07:00
remsky
d20da2f92e
Default hexxgrad voicepacks added as temporary fix
2025-01-15 09:42:27 +00:00
remsky
23c2ff2eaf
Update docker-compose.yml
2025-01-15 02:26:28 -07:00
remsky
363b55e8e5
Update docker-compose.yml
2025-01-15 02:26:10 -07:00
jteijema
aefd525c89
Update spacing in the readme
2025-01-14 16:39:17 +01:00
jteijema
55ea0db7df
Update GPU compose
2025-01-14 16:36:55 +01:00
jteijema
a1e01dbdbe
Update the readme
2025-01-14 16:30:06 +01:00
jteijema
0db7b73678
Flexible UI port
2025-01-14 16:14:44 +01:00
remsky
5fc36961ac
Merge pull request #50 from jteijema/patch-1
...
Update README.md with new local endpoint usage example
2025-01-14 08:03:43 -07:00
Jelle Teijema
a51ea53b50
Update README.md with new local endpoint usage example
...
The old method will result in a deprecation warning, this is the recommended method via openAI.
```python
@deprecated(
"Due to a bug, this method doesn't actually stream the response content, `.with_streaming_response.method()` should be used instead"
)
def stream_to_file(
...
```
2025-01-14 15:53:39 +01:00
remsky
880fa7ad53
fix: revert to working docker-slim config
2025-01-14 07:30:23 -07:00
remsky
ef12a9c05f
fix: properly expose and probe HTTP port for FastAPI
2025-01-14 07:17:57 -07:00
remsky
6fe35ac0ed
fix: enable HTTP probing for FastAPI endpoints
2025-01-14 07:02:21 -07:00
