0.15.1 +Fixes #24, no deepspeed by default, you're on your own for now

README.md

@@ -29,6 +29,10 @@ If you find a better voice match for `tts-1` or `tts-1-hd`, please let me know s
 
 ## Recent Changes
 
+Version 0.15.1, 2024-06-27
+
+* Remove deepspeed from requirements.txt, it's too complex for typical users. A more detailed deepspeed install document will be required.
+
 Version 0.15.0, 2024-06-26
 
 * Switch to [coqui-tts](https://github.com/idiap/coqui-ai-TTS) (updated fork), updated simpler dependencies, torch 2.3, etc.

requirements-rocm.txt

@@ -3,6 +3,7 @@ uvicorn
 loguru
 piper-tts
 coqui-tts
-deepspeed
+# Creating an environment where deepspeed works is complex, for now it will be disabled by default.
+#deepspeed
 torch; --index-url https://download.pytorch.org/whl/rocm5.7; sys_platform == "linux"
 torchaudio; --index-url https://download.pytorch.org/whl/rocm5.7; sys_platform == "linux"

requirements.txt

@@ -3,7 +3,8 @@ uvicorn
 loguru
 piper-tts
 coqui-tts[languages]
-deepspeed
+# Creating an environment where deepspeed works is complex, for now it will be disabled by default.
+#deepspeed
 
 torch; sys_platform != "darwin"
 torchaudio; sys_platform != "darwin"

speech.py

@@ -315,7 +315,7 @@ def auto_torch_device():
     parser.add_argument('--xtts_device', action='store', default=auto_torch_device(), help="Set the device for the xtts model. The special value of 'none' will use piper for all models.")
     parser.add_argument('--preload', action='store', default=None, help="Preload a model (Ex. 'xtts' or 'xtts_v2.0.2'). By default it's loaded on first use.")
     parser.add_argument('--unload-timer', action='store', default=None, type=int, help="Idle unload timer for the XTTS model in seconds")
-    parser.add_argument('--use-deepspeed', action='store_true', default=False, help="Use deepspeed for faster generation and lower VRAM usage in xtts")
+    parser.add_argument('--use-deepspeed', action='store_true', default=False, help="Use deepspeed with xtts (this option is unsupported)")
     parser.add_argument('-P', '--port', action='store', default=8000, type=int, help="Server tcp port")
     parser.add_argument('-H', '--host', action='store', default='0.0.0.0', help="Host to listen on, Ex. 0.0.0.0")
     parser.add_argument('-L', '--log-level', default="INFO", choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"], help="Set the log level")