File size: 15,066 Bytes
14100c7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
import os
import sys
import subprocess
from huggingface_hub import hf_hub_download
from pydub import AudioSegment
import gradio as gr
import time

# Thêm thư mục src vào sys.path
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), 'src')))

def run_f5_tts(ref_audio_path, ref_text, gen_text, model="F5TTS_Base", speed=1.2, vocoder_name="vocos"):
    current_dir = os.path.dirname(os.path.abspath(__file__))
    infer_cli_path = os.path.join(current_dir, "src", "f5_tts", "infer", "infer_cli.py")
    tests_dir = os.path.join(current_dir, "tests")

    print(f"Infer CLI path: {infer_cli_path}")
    print(f"Does infer_cli.py exist? {os.path.exists(infer_cli_path)}")
    if not os.path.exists(infer_cli_path):
        return None, "File infer_cli.py không tồn tại!"

    try:
        vocab_file = hf_hub_download(repo_id="nguyensu27/TTS", filename="vocab.txt")
        ckpt_file = hf_hub_download(repo_id="nguyensu27/TTS", filename="model_last.pt")
    except Exception as e:
        return None, f"Lỗi khi tải model/vocab: {str(e)}"

    os.environ['PYTHONIOENCODING'] = 'utf-8'
    env = os.environ.copy()
    env['PYTHONPATH'] = os.path.abspath(os.path.join(current_dir, 'src'))

    command = [
        sys.executable,
        infer_cli_path,
        "--model", model,
        "--ref_audio", ref_audio_path,
        "--ref_text", ref_text,
        "--gen_text", gen_text,
        "--speed", str(speed),
        "--vocoder_name", vocoder_name,
        "--vocab_file", vocab_file,
        "--ckpt_file", ckpt_file
    ]

    print(f"Running command: {' '.join(command)}")
    try:
        result = subprocess.run(
            command,
            check=True,
            capture_output=True,
            text=True,
            env=env
        )
        print("Subprocess stdout:", result.stdout)
        if os.path.exists(tests_dir):
            wav_files = [f for f in os.listdir(tests_dir) if f.endswith('.wav')]
            if wav_files:
                latest_wav = max(wav_files, key=lambda x: os.path.getmtime(os.path.join(tests_dir, x)))
                output_wav = os.path.join(tests_dir, latest_wav)
                audio = AudioSegment.from_wav(output_wav)
                output_mp3 = os.path.join(tests_dir, "output.mp3")
                audio.export(output_mp3, format="mp3")
                return output_mp3, "Suy luận thành công!"
        return None, "Không tìm thấy file âm thanh trong thư mục tests"
    except subprocess.CalledProcessError as e:
        return None, f"Lỗi khi chạy infer_cli.py: {e.stderr}"
    except Exception as e:
        return None, str(e)

def generate_speech(ref_audio, ref_text, gen_text, speed, model):
    if ref_audio is None:
        return None, "Vui lòng tải lên file audio tham chiếu!"
    # ref_audio là đường dẫn file, tải bằng AudioSegment
    audio_segment = AudioSegment.from_file(ref_audio)
    audio_segment = audio_segment.set_channels(1)  # Chuyển sang mono
    ref_audio_path = f"temp_ref_{int(time.time())}.wav"
    audio_segment.export(ref_audio_path, format="wav")

    output_mp3, message = run_f5_tts(ref_audio_path, ref_text, gen_text, model, float(speed))
    os.remove(ref_audio_path)

    if output_mp3 and os.path.exists(output_mp3):
        return output_mp3, message
    return None, message

interface = gr.Interface(
    fn=generate_speech,
    inputs=[
        gr.Audio(type="filepath", label="Tải lên file audio tham chiếu (.wav hoặc .mp3)"),
        gr.Textbox(label="Text tham chiếu", placeholder="Nhập text của audio tham chiếu"),
        gr.Textbox(label="Text cần sinh", placeholder="Nhập text bạn muốn sinh"),
        gr.Slider(minimum=0.5, maximum=2.0, value=1.0, label="Tốc độ"),
        gr.Dropdown(choices=["F5TTS_Base"], value="F5TTS_Base", label="Mô hình")
    ],
    outputs=[
        gr.Audio(type="filepath", label="Kết quả audio (.mp3)"),
        gr.Textbox(label="Trạng thái")
    ],
    title="F5-TTS Suy luận",
    description="Tải lên audio tham chiếu, nhập text, và sinh audio mới với F5-TTS."
)

if __name__ == "__main__":
    interface.launch(server_name="0.0.0.0", server_port=7860)



# import os
# import sys
# import subprocess
# from huggingface_hub import hf_hub_download
# from pydub import AudioSegment
# import gradio as gr
# import time

# # Thêm thư mục src vào sys.path
# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), 'src')))

# def run_f5_tts(ref_audio_path, ref_text, gen_text, model="F5TTS_Base", speed=1.2, vocoder_name="vocos"):
#     current_dir = os.path.dirname(os.path.abspath(__file__))
#     infer_cli_path = os.path.join(current_dir, "src", "f5_tts", "infer", "infer_cli.py")
#     tests_dir = os.path.join(current_dir, "tests")

#     # Debug: In đường dẫn để kiểm tra
#     print(f"Infer CLI path: {infer_cli_path}")
#     print(f"Tests dir: {tests_dir}")

#     # Tải file từ Hugging Face Hub
#     try:
#         vocab_file = hf_hub_download(repo_id="nguyensu27/TTS", filename="vocab.txt")
#         ckpt_file = hf_hub_download(repo_id="nguyensu27/TTS", filename="model_last.pt")
#     except Exception as e:
#         return None, f"Lỗi khi tải model/vocab từ Hugging Face: {str(e)}"

#     os.environ['PYTHONIOENCODING'] = 'utf-8'
#     env = os.environ.copy()
#     env['PYTHONPATH'] = os.path.abspath(os.path.join(current_dir, 'src'))

#     command = [
#         sys.executable,
#         infer_cli_path,
#         "--model", model,
#         "--ref_audio", ref_audio_path,
#         "--ref_text", ref_text,
#         "--gen_text", gen_text,
#         "--speed", str(speed),
#         "--vocoder_name", vocoder_name,
#         "--vocab_file", vocab_file,
#         "--ckpt_file", ckpt_file
#     ]

#     print(f"Running command: {' '.join(command)}")
#     try:
#         result = subprocess.run(
#             command,
#             check=True,
#             capture_output=True,
#             text=True,
#             env=env
#         )
#         print("Subprocess stdout:", result.stdout)
#         if os.path.exists(tests_dir):
#             wav_files = [f for f in os.listdir(tests_dir) if f.endswith('.wav')]
#             if wav_files:
#                 latest_wav = max(wav_files, key=lambda x: os.path.getmtime(os.path.join(tests_dir, x)))
#                 output_wav = os.path.join(tests_dir, latest_wav)
#                 audio = AudioSegment.from_wav(output_wav)
#                 output_mp3 = os.path.join(tests_dir, "output.mp3")
#                 audio.export(output_mp3, format="mp3")
#                 return output_mp3, "Suy luận thành công!"

#         return None, "Không tìm thấy file âm thanh trong thư mục tests"
#     except subprocess.CalledProcessError as e:
#         return None, f"Lỗi khi chạy infer_cli.py: {e.stderr}"
#     except Exception as e:
#         return None, str(e)

# def generate_speech(ref_audio, ref_text, gen_text, speed, model):
#     if ref_audio is None:
#         return None, "Vui lòng tải lên file audio tham chiếu!"
#     ref_audio_path = f"temp_ref_{int(time.time())}.wav"
#     ref_audio.convert_audio_channels(1)  # Chuyển sang mono
#     ref_audio.export(ref_audio_path, format="wav")

#     output_mp3, message = run_f5_tts(ref_audio_path, ref_text, gen_text, model, float(speed))
#     os.remove(ref_audio_path)

#     if output_mp3 and os.path.exists(output_mp3):
#         return output_mp3, message
#     return None, message

# interface = gr.Interface(
#     fn=generate_speech,
#     inputs=[
#         gr.Audio(type="filepath", label="Tải lên file audio tham chiếu (.wav hoặc .mp3)"),
#         gr.Textbox(label="Text tham chiếu", placeholder="Nhập text của audio tham chiếu"),
#         gr.Textbox(label="Text cần sinh", placeholder="Nhập text bạn muốn sinh"),
#         gr.Slider(minimum=0.5, maximum=2.0, value=1.0, label="Tốc độ"),
#         gr.Dropdown(choices=["F5TTS_Base"], value="F5TTS_Base", label="Mô hình")
#     ],
#     outputs=[
#         gr.Audio(type="filepath", label="Kết quả audio (.mp3)"),
#         gr.Textbox(label="Trạng thái")
#     ],
#     title="F5-TTS Suy luận",
#     description="Tải lên audio tham chiếu, nhập text, và sinh audio mới với F5-TTS."
# )

# if __name__ == "__main__":
#     interface.launch(server_name="0.0.0.0", server_port=7860)




# from flask import Flask, request, send_file
# import subprocess
# import os
# import sys
# from huggingface_hub import hf_hub_download
# from pydub import AudioSegment

# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), 'src')))

# app = Flask(__name__)

# def run_f5_tts(ref_audio_path, ref_text, gen_text, model="F5TTS_Base", speed=1.2, vocoder_name="vocos"):
#     current_dir = os.path.dirname(os.path.abspath(__file__))
#     infer_cli_path = os.path.join(current_dir, "src", "f5_tts", "infer", "infer_cli.py")
#     tests_dir = os.path.join(current_dir, "tests")

#     vocab_file = hf_hub_download(repo_id="nguyensu27/TTS", filename="vocab.txt")
#     ckpt_file = hf_hub_download(repo_id="nguyensu27/TTS", filename="model_last.pt")

#     os.environ['PYTHONIOENCODING'] = 'utf-8'
#     env = os.environ.copy()
#     env['PYTHONPATH'] = os.path.abspath(os.path.join(current_dir, 'src'))

#     command = [
#         sys.executable,
#         infer_cli_path,
#         "--model", model,
#         "--ref_audio", ref_audio_path,
#         "--ref_text", ref_text,
#         "--gen_text", gen_text,
#         "--speed", str(speed),
#         "--vocoder_name", vocoder_name,
#         "--vocab_file", vocab_file,
#         "--ckpt_file", ckpt_file
#     ]

#     try:
#         result = subprocess.run(
#             command,
#             check=True,
#             capture_output=True,
#             text=True,
#             encoding='utf-8',
#             env=env
#         )

#         if os.path.exists(tests_dir):
#             wav_files = [f for f in os.listdir(tests_dir) if f.endswith('.wav')]
#             if wav_files:
#                 latest_wav = max(wav_files, key=lambda x: os.path.getmtime(os.path.join(tests_dir, x)))
#                 output_wav = os.path.join(tests_dir, latest_wav)
#                 audio = AudioSegment.from_wav(output_wav)
#                 output_mp3 = os.path.join(tests_dir, "output.mp3")
#                 audio.export(output_mp3, format="mp3")
#                 return True, output_mp3

#         return False, "Không tìm thấy file âm thanh trong thư mục tests"
#     except subprocess.CalledProcessError as e:
#         return False, f"Lỗi khi chạy infer_cli.py: {e.stderr}"
#     except Exception as e:
#         return False, str(e)

# @app.route('/')
# def home():
#     return "F5-TTS API is running. Use POST /api/generate to generate audio."

# @app.route('/api/generate', methods=['POST'])
# def generate_speech():
#     if 'ref_audio' not in request.files:
#         return {"error": "Missing ref_audio"}, 400
#     ref_audio = request.files['ref_audio']
#     ref_text = request.form.get('ref_text', '')
#     gen_text = request.form.get('gen_text', '')
#     model = request.form.get('model', 'F5TTS_Base')
#     speed = float(request.form.get('speed', 1.2))

#     import time
#     ref_audio_path = f"temp_ref_{int(time.time())}.wav"
#     ref_audio.save(ref_audio_path)

#     success, result = run_f5_tts(ref_audio_path, ref_text, gen_text, model, speed)
#     os.remove(ref_audio_path)

#     if success:
#         return send_file(result, mimetype='audio/mpeg')
#     else:
#         return {"error": result}, 500

# if __name__ == "__main__":
#     port = int(os.environ.get("PORT", 7860))
#     app.run(host="0.0.0.0", port=port, debug=False)



# from flask import Flask, request, send_file
# import subprocess
# import os
# import sys
# from huggingface_hub import hf_hub_download
# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), 'src')))

# app = Flask(__name__)

# # =========================
# # Hàm chạy F5-TTS
# # =========================
# def run_f5_tts(ref_audio_path, ref_text, gen_text, model="F5TTS_Base", speed=1.2, vocoder_name="vocos"):
#     current_dir = os.path.dirname(os.path.abspath(__file__))
#     infer_cli_path = os.path.join(current_dir, "src", "f5_tts", "infer", "infer_cli.py")
#     tests_dir = os.path.join(current_dir, "tests")

#     # Dùng huggingface_hub để tải file model và vocab từ repo 'nguyensu27/TTS'
#     vocab_file = hf_hub_download(repo_id="nguyensu27/TTS", filename="vocab.txt")
#     ckpt_file = hf_hub_download(repo_id="nguyensu27/TTS", filename="model_last.pt")

#     os.environ['PYTHONIOENCODING'] = 'utf-8'

#     command = [
#         sys.executable,
#         infer_cli_path,
#         "--model", model,
#         "--ref_audio", ref_audio_path,
#         "--ref_text", ref_text,
#         "--gen_text", gen_text,
#         "--speed", str(speed),
#         "--vocoder_name", vocoder_name,
#         "--vocab_file", vocab_file,
#         "--ckpt_file", ckpt_file
#     ]

#     try:
#         result = subprocess.run(
#             command,
#             check=True,
#             capture_output=True,
#             text=True,
#             encoding='utf-8'
#         )

#         if os.path.exists(tests_dir):
#             wav_files = [f for f in os.listdir(tests_dir) if f.endswith('.wav')]
#             if wav_files:
#                 latest_wav = max(
#                     wav_files, key=lambda x: os.path.getmtime(os.path.join(tests_dir, x))
#                 )
#                 output_file = os.path.join(tests_dir, latest_wav)
#                 return True, output_file

#         return False, "Không tìm thấy file âm thanh trong thư mục tests"
#     except subprocess.CalledProcessError as e:
#         return False, e.stderr
#     except Exception as e:
#         return False, str(e)


# # =========================
# # Routes
# # =========================
# @app.route('/')
# def home():
#     return "F5-TTS API is running. Use POST /api/generate to generate audio."


# @app.route('/api/generate', methods=['POST'])
# def generate_speech():
#     if 'ref_audio' not in request.files:
#         return {"error": "Missing ref_audio"}, 400
#     ref_audio = request.files['ref_audio']
#     ref_text = request.form.get('ref_text', '')
#     gen_text = request.form.get('gen_text', '')
#     model = request.form.get('model', 'F5TTS_Base')
#     speed = float(request.form.get('speed', 1.2))

#     ref_audio_path = 'temp_ref.wav'
#     ref_audio.save(ref_audio_path)

#     success, result = run_f5_tts(ref_audio_path, ref_text, gen_text, model, speed)
#     os.remove(ref_audio_path)

#     if success:
#         return send_file(result, mimetype='audio/wav')
#     else:
#         return {"error": result}, 500


# # =========================
# # Main
# # =========================
# if __name__ == "__main__":
#     port = int(os.environ.get("PORT", 7860))
#     app.run(host="0.0.0.0", port=port, debug=False)