BatchalignHK 0.7.19.post18__tar.gz → 0.7.19.post20__tar.gz

{batchalignhk-0.7.19.post18 → batchalignhk-0.7.19.post20}/BatchalignHK.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: BatchalignHK
-Version: 0.7.19.post18
+Version: 0.7.19.post20
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -37,6 +37,8 @@ Requires-Dist: sentencepiece
 Requires-Dist: tencentcloud-sdk-python-common
 Requires-Dist: tencentcloud-sdk-python-asr
 Requires-Dist: googletrans
+Requires-Dist: aliyun-python-sdk-core>=2.13.3
+Requires-Dist: oss2
 Requires-Dist: openai-whisper>=20240930
 Provides-Extra: dev
 Requires-Dist: pytest; extra == "dev"
@@ -64,7 +66,7 @@ The TalkBank Project, of which Batchalign is a part, is supported by NIH grant H
 
 ## Quick Start
 
-The following instructions provide a quick start to installing Batchalign. For most users aiming to process CHAT and audio with Batchalign, we recommend more detailed usage instructions: for [usage](https://talkbank.org/info/BA2-usage.pdf) and [human transcript cleanup](https://talkbank.org/info/BA2-cleanup.pdf). The following provides a quick start guide for the program.
+The following instructions provide a quick start to installing Batchalign. For most users aiming to process CHAT and audio with Batchalign, we recommend more detailed usage instructions: for [usage](https://talkbank.org/0info/BA2-usage.pdf) and [human transcript cleanup](https://talkbank.org/0info/BA2-cleanup.pdf). The following provides a quick start guide for the program.
 
 ### Install and Update the Package
 Batchalign is on PyPi (as `batchalign`). We recommend the use of UV to install Batchalign:

{batchalignhk-0.7.19.post18 → batchalignhk-0.7.19.post20}/BatchalignHK.egg-info/SOURCES.txt

@@ -17,6 +17,39 @@ batchalign/version
 batchalign/cli/__init__.py
 batchalign/cli/cli.py
 batchalign/cli/dispatch.py
+batchalign/extern/nls/__init__.py
+batchalign/extern/nls/core.py
+batchalign/extern/nls/exception.py
+batchalign/extern/nls/logging.py
+batchalign/extern/nls/realtime_meeting.py
+batchalign/extern/nls/speech_recognizer.py
+batchalign/extern/nls/speech_synthesizer.py
+batchalign/extern/nls/speech_transcriber.py
+batchalign/extern/nls/stream_input_tts.py
+batchalign/extern/nls/token.py
+batchalign/extern/nls/util.py
+batchalign/extern/nls/version.py
+batchalign/extern/nls/websocket/__init__.py
+batchalign/extern/nls/websocket/_abnf.py
+batchalign/extern/nls/websocket/_app.py
+batchalign/extern/nls/websocket/_cookiejar.py
+batchalign/extern/nls/websocket/_core.py
+batchalign/extern/nls/websocket/_exceptions.py
+batchalign/extern/nls/websocket/_handshake.py
+batchalign/extern/nls/websocket/_http.py
+batchalign/extern/nls/websocket/_logging.py
+batchalign/extern/nls/websocket/_socket.py
+batchalign/extern/nls/websocket/_ssl_compat.py
+batchalign/extern/nls/websocket/_url.py
+batchalign/extern/nls/websocket/_utils.py
+batchalign/extern/nls/websocket/tests/__init__.py
+batchalign/extern/nls/websocket/tests/echo-server.py
+batchalign/extern/nls/websocket/tests/test_abnf.py
+batchalign/extern/nls/websocket/tests/test_app.py
+batchalign/extern/nls/websocket/tests/test_cookiejar.py
+batchalign/extern/nls/websocket/tests/test_http.py
+batchalign/extern/nls/websocket/tests/test_url.py
+batchalign/extern/nls/websocket/tests/test_websocket.py
 batchalign/formats/__init__.py
 batchalign/formats/base.py
 batchalign/formats/chat/__init__.py
@@ -58,6 +91,7 @@ batchalign/pipelines/pipeline.py
 batchalign/pipelines/analysis/__init__.py
 batchalign/pipelines/analysis/eval.py
 batchalign/pipelines/asr/__init__.py
+batchalign/pipelines/asr/aliyun.py
 batchalign/pipelines/asr/num2chinese.py
 batchalign/pipelines/asr/oai_whisper.py
 batchalign/pipelines/asr/rev.py

{batchalignhk-0.7.19.post18 → batchalignhk-0.7.19.post20}/BatchalignHK.egg-info/requires.txt

@@ -27,6 +27,8 @@ sentencepiece
 tencentcloud-sdk-python-common
 tencentcloud-sdk-python-asr
 googletrans
+aliyun-python-sdk-core>=2.13.3
+oss2
 openai-whisper>=20240930
 
 [dev]

{batchalignhk-0.7.19.post18 → batchalignhk-0.7.19.post20}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: BatchalignHK
-Version: 0.7.19.post18
+Version: 0.7.19.post20
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -37,6 +37,8 @@ Requires-Dist: sentencepiece
 Requires-Dist: tencentcloud-sdk-python-common
 Requires-Dist: tencentcloud-sdk-python-asr
 Requires-Dist: googletrans
+Requires-Dist: aliyun-python-sdk-core>=2.13.3
+Requires-Dist: oss2
 Requires-Dist: openai-whisper>=20240930
 Provides-Extra: dev
 Requires-Dist: pytest; extra == "dev"
@@ -64,7 +66,7 @@ The TalkBank Project, of which Batchalign is a part, is supported by NIH grant H
 
 ## Quick Start
 
-The following instructions provide a quick start to installing Batchalign. For most users aiming to process CHAT and audio with Batchalign, we recommend more detailed usage instructions: for [usage](https://talkbank.org/info/BA2-usage.pdf) and [human transcript cleanup](https://talkbank.org/info/BA2-cleanup.pdf). The following provides a quick start guide for the program.
+The following instructions provide a quick start to installing Batchalign. For most users aiming to process CHAT and audio with Batchalign, we recommend more detailed usage instructions: for [usage](https://talkbank.org/0info/BA2-usage.pdf) and [human transcript cleanup](https://talkbank.org/0info/BA2-cleanup.pdf). The following provides a quick start guide for the program.
 
 ### Install and Update the Package
 Batchalign is on PyPi (as `batchalign`). We recommend the use of UV to install Batchalign:

{batchalignhk-0.7.19.post18 → batchalignhk-0.7.19.post20}/README.md

@@ -8,7 +8,7 @@ The TalkBank Project, of which Batchalign is a part, is supported by NIH grant H
 
 ## Quick Start
 
-The following instructions provide a quick start to installing Batchalign. For most users aiming to process CHAT and audio with Batchalign, we recommend more detailed usage instructions: for [usage](https://talkbank.org/info/BA2-usage.pdf) and [human transcript cleanup](https://talkbank.org/info/BA2-cleanup.pdf). The following provides a quick start guide for the program.
+The following instructions provide a quick start to installing Batchalign. For most users aiming to process CHAT and audio with Batchalign, we recommend more detailed usage instructions: for [usage](https://talkbank.org/0info/BA2-usage.pdf) and [human transcript cleanup](https://talkbank.org/0info/BA2-cleanup.pdf). The following provides a quick start guide for the program.
 
 ### Install and Update the Package
 Batchalign is on PyPi (as `batchalign`). We recommend the use of UV to install Batchalign:

{batchalignhk-0.7.19.post18 → batchalignhk-0.7.19.post20}/batchalign/cli/cli.py

@@ -160,6 +160,8 @@ def align(ctx, in_dir, out_dir, whisper, wav2vec, tencent, **kwargs):
               default=False, help="Use Tencent instead of Rev.AI (default).")
 @click.option("--whisperx/--rev",
               default=False, help="Use WhisperX instead of Rev.AI (default). Superceeds --whisper.")
+@click.option("--alibaba/--rev",
+              default=False, help="Use Alibaba instead of Rev.AI (default). Superceeds --whisper.")
 @click.option("--diarize/--nodiarize",
               default=False, help="Perform speaker diarization (this flag is ignored with Rev.AI)")
 @click.option("--wor/--nowor",
@@ -188,6 +190,8 @@ def transcribe(ctx, in_dir, out_dir, lang, num_speakers, **kwargs):
         asr = "tencent"
     if kwargs["whisper_oai"]:
         asr = "whisper_oai"
+    if kwargs["alibaba"]:
+        asr = "aliyun"
 
     def writer(doc, output):
         doc.content.insert(0, CustomLine(id="Comment", type=CustomLineType.INDEPENDENT,

batchalignhk-0.7.19.post20/batchalign/extern/nls/__init__.py

@@ -0,0 +1,10 @@
+# Copyright (c) Alibaba, Inc. and its affiliates.
+
+from .logging import *
+from .speech_recognizer import *
+from .speech_transcriber import *
+from .speech_synthesizer import *
+from .stream_input_tts import *
+from .realtime_meeting import *
+from .util import *
+from .version import __version__

batchalignhk-0.7.19.post20/batchalign/extern/nls/core.py

@@ -0,0 +1,183 @@
+# Copyright (c) Alibaba, Inc. and its affiliates.
+
+import logging
+import threading
+
+from enum import Enum, unique
+from queue import Queue
+
+from . import logging, token, websocket
+from .exception import InvalidParameter, ConnectionTimeout, ConnectionUnavailable
+
+__URL__ = 'wss://nls-gateway.cn-shanghai.aliyuncs.com/ws/v1'
+__HEADER__ = [
+    'Sec-WebSocket-Key: x3JJHMbDL1EzLkh9GBhXDw==',
+    'Sec-WebSocket-Version: 13',
+]
+
+__FORMAT__ = '%(asctime)s - %(levelname)s - %(message)s'
+#__all__ = ['NlsCore']
+
+def core_on_msg(ws, message, args):
+    logging.debug('core_on_msg:{}'.format(message))
+    if not args:
+        logging.error('callback core_on_msg with null args')
+        return
+    nls = args[0]
+    nls._NlsCore__issue_callback('on_message', [message])
+
+def core_on_error(ws, message, args):
+    logging.debug('core_on_error:{}'.format(message))
+    if not args:
+        logging.error('callback core_on_error with null args')
+        return
+    nls = args[0]
+    nls._NlsCore__issue_callback('on_error', [message])
+
+def core_on_close(ws, close_status_code, close_msg, args):
+    logging.debug('core_on_close')
+    if not args:
+        logging.error('callback core_on_close with null args')
+        return
+    nls = args[0]
+    nls._NlsCore__issue_callback('on_close')
+
+def core_on_open(ws, args):
+    logging.debug('core_on_open:{}'.format(args))
+    if not args:
+        logging.debug('callback with null args')
+        ws.close()
+    elif len(args) != 2:
+        logging.debug('callback args not 2')
+        ws.close()
+    nls = args[0]
+    nls._NlsCore__notify_on_open()
+    nls.start(args[1], nls._NlsCore__ping_interval, nls._NlsCore__ping_timeout)
+    nls._NlsCore__issue_callback('on_open')
+
+def core_on_data(ws, data, opcode, flag, args):
+    logging.debug('core_on_data opcode={}'.format(opcode))
+    if not args:
+        logging.error('callback core_on_data with null args')
+        return
+    nls = args[0]
+    nls._NlsCore__issue_callback('on_data', [data, opcode, flag])
+
+@unique
+class NlsConnectionStatus(Enum):
+    Disconnected = 0
+    Connected = 1
+
+
+class NlsCore:
+    """
+    NlsCore
+    """
+    def __init__(self, 
+                 url=__URL__,
+                 token=None,
+                 on_open=None, on_message=None, on_close=None,
+                 on_error=None, on_data=None, asynch=False, callback_args=[]):
+        self.__url = url
+        self.__async = asynch
+        if not token:
+            raise InvalidParameter('Must provide a valid token!')
+        else:
+            self.__token = token
+        self.__callbacks = {}
+        if on_open:
+            self.__callbacks['on_open'] = on_open
+        if on_message:
+            self.__callbacks['on_message'] = on_message
+        if on_close:
+            self.__callbacks['on_close'] = on_close
+        if on_error:
+            self.__callbacks['on_error'] = on_error
+        if on_data:
+            self.__callbacks['on_data'] = on_data
+        if not on_open and not on_message and not on_close and not on_error:
+            raise InvalidParameter('Must provide at least one callback')
+        logging.debug('callback args:{}'.format(callback_args))
+        self.__callback_args = callback_args
+        self.__header = __HEADER__ + ['X-NLS-Token: {}'.format(self.__token)]
+        websocket.enableTrace(True)
+        self.__ws = websocket.WebSocketApp(self.__url,
+                                           self.__header,
+                                           on_message=core_on_msg,
+                                           on_data=core_on_data,
+                                           on_error=core_on_error,
+                                           on_close=core_on_close,
+                                           callback_args=[self])
+        self.__ws.on_open = core_on_open
+        self.__lock = threading.Lock()
+        self.__cond = threading.Condition()
+        self.__connection_status = NlsConnectionStatus.Disconnected
+
+    def start(self, msg, ping_interval, ping_timeout):
+        self.__lock.acquire()
+        self.__ping_interval = ping_interval
+        self.__ping_timeout = ping_timeout
+        if self.__connection_status == NlsConnectionStatus.Disconnected:
+            self.__ws.update_args(self, msg)
+            self.__lock.release()
+            self.__connect_before_start(ping_interval, ping_timeout)
+        else:
+            self.__lock.release()
+            self.__ws.send(msg)
+
+    def __notify_on_open(self):
+        logging.debug('notify on open')
+        with self.__cond:
+            self.__connection_status = NlsConnectionStatus.Connected
+            self.__cond.notify()
+
+    def __issue_callback(self, which, exargs=[]):
+        if which not in self.__callbacks:
+            logging.error('no such callback:{}'.format(which))
+            return
+        if which == 'on_close':
+            with self.__cond:
+                self.__connection_status = NlsConnectionStatus.Disconnected
+                self.__cond.notify()
+        args = exargs+self.__callback_args
+        self.__callbacks[which](*args)
+
+    def send(self, msg, binary):
+        self.__lock.acquire()
+        if self.__connection_status == NlsConnectionStatus.Disconnected:
+            self.__lock.release()
+            logging.error('start before send')
+            raise ConnectionUnavailable('Must call start before send!')
+        else:
+            self.__lock.release()
+            if binary:
+                self.__ws.send(msg, opcode=websocket.ABNF.OPCODE_BINARY)
+            else:
+                logging.debug('send {}'.format(msg))
+                self.__ws.send(msg)
+    
+    def shutdown(self):
+        self.__ws.close()
+
+    def __run(self, ping_interval, ping_timeout):
+        logging.debug('ws run...')
+        self.__ws.run_forever(ping_interval=ping_interval,
+                ping_timeout=ping_timeout)
+        with self.__lock:
+            self.__connection_status = NlsConnectionStatus.Disconnected
+        logging.debug('ws exit...')
+
+    def __connect_before_start(self, ping_interval, ping_timeout):
+        with self.__cond:
+            self.__th = threading.Thread(target=self.__run,
+                    args=[ping_interval, ping_timeout])
+            self.__th.start()
+            if self.__connection_status == NlsConnectionStatus.Disconnected:
+                logging.debug('wait cond wakeup')
+                if not self.__async:
+                    if self.__cond.wait(timeout=10):
+                        logging.debug('wakeup without timeout')
+                        return self.__connection_status == NlsConnectionStatus.Connected
+                    else:
+                        logging.debug('wakeup with timeout')
+                        raise ConnectionTimeout('Wait response timeout! Please check local network!')

batchalignhk-0.7.19.post20/batchalign/extern/nls/exception.py

@@ -0,0 +1,31 @@
+# Copyright (c) Alibaba, Inc. and its affiliates.
+
+
+class InvalidParameter(Exception):
+    pass
+
+# Token
+class GetTokenFailed(Exception):
+    pass
+
+# Connection
+class ConnectionTimeout(Exception):
+    pass
+
+class ConnectionUnavailable(Exception):
+    pass
+
+class StartTimeoutException(Exception):
+    pass
+
+class StopTimeoutException(Exception):
+    pass
+
+class NotStartException(Exception):
+    pass
+
+class CompleteTimeoutException(Exception):
+    pass
+
+class WrongStateException(Exception):
+    pass

batchalignhk-0.7.19.post20/batchalign/extern/nls/logging.py

@@ -0,0 +1,65 @@
+# Copyright (c) Alibaba, Inc. and its affiliates.
+
+import logging
+
+_logger = logging.getLogger('nls')
+
+try:
+    from logging import NullHandler
+except ImportError:
+    class NullHandler(logging.Handler):
+        def emit(self, record):
+            pass
+
+_logger.addHandler(NullHandler())
+_traceEnabled = False
+__LOG_FORMAT__ = '%(asctime)s - %(levelname)s - %(message)s'
+
+__all__=['enableTrace', 'dump', 'error', 'warning', 'debug', 'trace',
+        'isEnabledForError', 'isEnabledForDebug', 'isEnabledForTrace']
+
+def enableTrace(traceable, handler=logging.StreamHandler()):
+    """
+    enable log print
+
+    Parameters
+    ----------
+    traceable: bool
+        whether enable log print, default log level is logging.DEBUG
+    handler: Handler object
+        handle how to print out log, default to stdio
+    """
+    global _traceEnabled
+    _traceEnabled = traceable
+    if traceable:
+        _logger.addHandler(handler)
+        _logger.setLevel(logging.DEBUG)
+        handler.setFormatter(logging.Formatter(__LOG_FORMAT__))
+
+def dump(title, message):
+    if _traceEnabled:
+        _logger.debug('### ' + title + ' ###')
+        _logger.debug(message)
+        _logger.debug('########################################')
+
+def error(msg):
+    _logger.error(msg)
+
+def warning(msg):
+    _logger.warning(msg)
+
+def debug(msg):
+    _logger.debug(msg)
+
+def trace(msg):
+    if _traceEnabled:
+        _logger.debug(msg)
+
+def isEnabledForError():
+    return _logger.isEnabledFor(logging.ERROR)
+
+def isEnabledForDebug():
+    return _logger.isEnabledFor(logging.Debug)
+
+def isEnabledForTrace():
+    return _traceEnabled