Merge branch 'main' of https://github.com/matatonic/openedai-speech

README.md

@@ -18,7 +18,7 @@ Details:
   * You can map your own [piper voices](https://rhasspy.github.io/piper-samples/) via the `voice_to_speaker.yaml` configuration file
 * Model `tts-1-hd` via [coqui-ai/TTS](https://github.com/coqui-ai/TTS) xtts_v2 voice cloning (fast, but requires around 4GB GPU VRAM)
   * Custom cloned voices can be used for tts-1-hd, See: [Custom Voices Howto](#custom-voices-howto)
-  * 🌐 [Multilingual](#multilingual) support with XTTS voices
+  * 🌐 [Multilingual](#multilingual) support with XTTS voices, the language is automatically detected if not set
   * [Custom fine-tuned XTTS model support](#custom-fine-tuned-model-support)
   * Configurable [generation parameters](#generation-parameters)
   * Streamed output while generating
@@ -30,6 +30,19 @@ If you find a better voice match for `tts-1` or `tts-1-hd`, please let me know s
 
 ## Recent Changes
 
+Version 0.17.2, 2024-07-01
+
+* fix -min image (re: langdetect)
+
+Version 0.17.1, 2024-07-01
+
+* fix ROCm (add langdetect to requirements-rocm.txt)
+* Fix zh-cn for xtts
+
+Version 0.17.0, 2024-07-01
+
+* Automatic language detection, thanks [@RodolfoCastanheira](https://github.com/RodolfoCastanheira)
+
 Version 0.16.0, 2024-06-29
 
 * Multi-client safe version. Audio generation is synchronized in a single process. The estimated 'realtime' factor of XTTS on a GPU is roughly 1/3, this means that multiple streams simultaneously, or `speed` over 2, may experience audio underrun (delays or pauses in playback). This makes multiple clients possible and safe, but in practice 2 or 3 simultaneous streams is the maximum without audio underrun.
@@ -58,7 +71,7 @@ Version 0.14.0, 2024-06-26
 Version 0.13.0, 2024-06-25
 
 * Added [Custom fine-tuned XTTS model support](#custom-fine-tuned-model-support)
-* Initial prebuilt arm64 image support (Apple M-series, Raspberry Pi - MPS is not supported in XTTS/torch), thanks @JakeStevenson, @hchasens
+* Initial prebuilt arm64 image support (Apple M-series, Raspberry Pi - MPS is not supported in XTTS/torch), thanks [@JakeStevenson](https://github.com/JakeStevenson), [@hchasens](https://github.com/hchasens)
 * Initial attempt at AMD GPU (ROCm 5.7) support
 * Parler-tts support removed
 * Move the *.default.yaml to the root folder
@@ -88,7 +101,7 @@ Version 0.11.0, 2024-05-29
 
 Version: 0.10.1, 2024-05-05
 
-* Remove `runtime: nvidia` from docker-compose.yml, this assumes nvidia/cuda compatible runtime is available by default. thanks @jmtatsch
+* Remove `runtime: nvidia` from docker-compose.yml, this assumes nvidia/cuda compatible runtime is available by default. thanks [@jmtatsch](https://github.com/jmtatsch)
 
 Version: 0.10.0, 2024-04-27
 
@@ -318,7 +331,7 @@ tts-1-hd:
 
 Multilingual cloning support was added in version 0.11.0 and is available only with the XTTS v2 model. To use multilingual voices with piper simply download a language specific voice.
 
-Coqui XTTSv2 has support for 16 languages: English (`en`), Spanish (`es`), French (`fr`), German (`de`), Italian (`it`), Portuguese (`pt`), Polish (`pl`), Turkish (`tr`), Russian (`ru`), Dutch (`nl`), Czech (`cs`), Arabic (`ar`), Chinese (`zh-cn`), Japanese (`ja`), Hungarian (`hu`) and Korean (`ko`).
+Coqui XTTSv2 has support for multiple languages: English (`en`), Spanish (`es`), French (`fr`), German (`de`), Italian (`it`), Portuguese (`pt`), Polish (`pl`), Turkish (`tr`), Russian (`ru`), Dutch (`nl`), Czech (`cs`), Arabic (`ar`), Chinese (`zh-cn`), Hungarian (`hu`), Korean (`ko`), Japanese (`ja`), and Hindi (`hi`). When not set, an attempt will be made to automatically detect the language, falling back to English (`en`).
 
 Unfortunately the OpenAI API does not support language, but you can create your own custom speaker voice and set the language for that.
 

add_voice.py

@@ -11,8 +11,8 @@ parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFo
 
 parser.add_argument('sample', action='store', help="Set the wav sample file")
 parser.add_argument('-n', '--name', action='store', help="Set the name for the voice (by default will use the WAV file name)")
-parser.add_argument('-l', '--language', action='store', default="en", help="Set the language for the voice",
-                    choices=['en', 'es', 'fr', 'de', 'it', 'pt', 'pl', 'tr', 'ru', 'nl', 'cs', 'ar', 'zh-cn', 'ja', 'hu', 'ko'])
+parser.add_argument('-l', '--language', action='store', default="auto", help="Set the language for the voice",
+                    choices=['auto', 'en', 'es', 'fr', 'de', 'it', 'pt', 'pl', 'tr', 'ru', 'nl', 'cs', 'ar', 'zh-cn', 'ja', 'hu', 'ko', 'hi'])
 parser.add_argument('--openai-model', action='store', default="tts-1-hd", help="Set the openai model for the voice")
 parser.add_argument('--xtts-model', action='store', default="xtts", help="Set the xtts model for the voice (if using a custom model, also set model_path)")
 parser.add_argument('--model-path', action='store', default=None, help="Set the path for a custom xtts model")

requirements-rocm.txt

@@ -3,6 +3,7 @@ uvicorn
 loguru
 piper-tts
 coqui-tts
+langdetect
 # 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"

requirements.txt

@@ -3,6 +3,7 @@ uvicorn
 loguru
 piper-tts
 coqui-tts[languages]
+langdetect
 # Creating an environment where deepspeed works is complex, for now it will be disabled by default.
 #deepspeed
 
@@ -12,4 +13,4 @@ torchaudio; sys_platform != "darwin"
 torch; --index-url https://download.pytorch.org/whl/cpu; sys_platform == "darwin"
 torchaudio; --index-url https://download.pytorch.org/whl/cpu; sys_platform == "darwin"
 
-# ROCM (Linux only) - use requirements.amd.txt
+# ROCM (Linux only) - use requirements.amd.txt

speech.py

@@ -17,7 +17,6 @@ from openedai import OpenAIStub, BadRequestError, ServiceUnavailableError
 from pydantic import BaseModel
 import uvicorn
 
-
 @contextlib.asynccontextmanager
 async def lifespan(app):
     yield
@@ -270,7 +269,21 @@ async def generate_speech(request: GenerateSpeechRequest):
         # Pipe the output from piper/xtts to the input of ffmpeg
         ffmpeg_args.extend(["-"])
 
-        language = voice_map.pop('language', 'en')
+        language = voice_map.pop('language', 'auto')
+        if language == 'auto':
+            try:
+                language = detect(input_text)
+                if language not in [
+                    'en', 'es', 'fr', 'de', 'it', 'pt', 'pl', 'tr',
+                    'ru', 'nl', 'cs', 'ar', 'zh-cn', 'hu', 'ko', 'ja', 'hi'
+                ]:
+                    logger.debug(f"Detected language {language} not supported, defaulting to en")
+                    language = 'en'
+                else:
+                    logger.debug(f"Detected language: {language}")
+            except:
+                language = 'en'
+                logger.debug(f"Failed to detect language, defaulting to en")
 
         comment = voice_map.pop('comment', None) # ignored.
 
@@ -282,7 +295,11 @@ async def generate_speech(request: GenerateSpeechRequest):
         hf_generate_kwargs['enable_text_splitting'] = hf_generate_kwargs.get('enable_text_splitting', True) # change the default to true
 
         if hf_generate_kwargs['enable_text_splitting']:
-            all_text = split_sentence(input_text, language, xtts.xtts.tokenizer.char_limits[language])
+            if language == 'zh-cn':
+                split_lang = 'zh'
+            else:
+                split_lang = language
+            all_text = split_sentence(input_text, split_lang, xtts.xtts.tokenizer.char_limits[split_lang])
         else:
             all_text = [input_text]
 
@@ -387,6 +404,7 @@ if __name__ == "__main__":
         from TTS.tts.models.xtts import Xtts
         from TTS.utils.manage import ModelManager
         from TTS.tts.layers.xtts.tokenizer import split_sentence
+        from langdetect import detect
 
     if args.preload:
         xtts = xtts_wrapper(args.preload, device=args.xtts_device, unload_timer=args.unload_timer)

voice_to_speaker.default.yaml

@@ -46,8 +46,9 @@ tts-1-hd:
     model: xtts
     speaker: voices/shimmer.wav
   me:
-    model: xtts_v2.0.2 # you can specify different xtts version
+    model: xtts_v2.0.2 # you can specify an older xtts version
     speaker: voices/me.wav # this could be you
+    language: auto
     enable_text_splitting: True
     length_penalty: 1.0
     repetition_penalty: 10